Upload folder using huggingface_hub

.vscode/launch.json

@@ -20,6 +20,7 @@
             "program": "tts_service/app.py",
             "args": ["--open"],
             "console": "integratedTerminal",
+            "envFile": "${workspaceFolder}/.env",
             "justMyCode": false
         }
     ]

logging.yml

@@ -0,0 +1,18 @@
+version: 1
+formatters:
+  simple:
+    format: '%(asctime)s %(levelname)s %(name)s - %(message)s'
+handlers:
+  console:
+    class: logging.StreamHandler
+    level: DEBUG
+    formatter: simple
+    stream: ext://sys.stdout
+loggers:
+  tts_service:
+    level: INFO
+    handlers: [console]
+    propagate: no
+root:
+  level: WARNING
+  handlers: [console]

notebooks/articles/sample-2.srt

@@ -0,0 +1,161 @@
+WEBVTT
+
+00:00:00.087 --> 00:00:00.750
+Thanksgiving
+
+00:00:00.762 --> 00:00:00.838
+in
+
+00:00:00.850 --> 00:00:01.450
+America
+
+00:00:01.462 --> 00:00:02.413
+2024
+
+00:00:02.938 --> 00:00:03.325
+Social
+
+00:00:03.337 --> 00:00:03.975
+devastation
+
+00:00:03.987 --> 00:00:04.100
+for
+
+00:00:04.112 --> 00:00:04.213
+the
+
+00:00:04.225 --> 00:00:04.600
+working
+
+00:00:04.612 --> 00:00:05.112
+class
+
+00:00:05.412 --> 00:00:05.875
+billions
+
+00:00:05.888 --> 00:00:06.162
+more
+
+00:00:06.175 --> 00:00:06.300
+for
+
+00:00:06.312 --> 00:00:06.400
+the
+
+00:00:06.412 --> 00:00:07.125
+oligarchs
+
+00:00:07.537 --> 00:00:07.662
+By
+
+00:00:07.675 --> 00:00:08.037
+Barry
+
+00:00:08.050 --> 00:00:08.475
+Grey
+
+00:00:08.875 --> 00:00:09.000
+On
+
+00:00:09.012 --> 00:00:09.625
+Thanksgiving
+
+00:00:09.637 --> 00:00:09.900
+Day
+
+00:00:09.912 --> 00:00:10.887
+2024
+
+00:00:11.250 --> 00:00:11.350
+the
+
+00:00:11.363 --> 00:00:11.738
+broad
+
+00:00:11.750 --> 00:00:12.125
+mass
+
+00:00:12.137 --> 00:00:12.213
+of
+
+00:00:12.225 --> 00:00:12.312
+the
+
+00:00:12.325 --> 00:00:12.787
+American
+
+00:00:12.800 --> 00:00:13.500
+population
+
+00:00:13.512 --> 00:00:13.738
+has
+
+00:00:13.750 --> 00:00:14.225
+precious
+
+00:00:14.238 --> 00:00:14.475
+little
+
+00:00:14.488 --> 00:00:14.550
+to
+
+00:00:14.562 --> 00:00:14.700
+be
+
+00:00:14.713 --> 00:00:15.188
+thankful
+
+00:00:15.200 --> 00:00:15.625
+for
+
+00:00:16.025 --> 00:00:16.488
+Inflated
+
+00:00:16.500 --> 00:00:16.850
+costs
+
+00:00:16.863 --> 00:00:17.050
+for
+
+00:00:17.062 --> 00:00:17.212
+all
+
+00:00:17.225 --> 00:00:17.925
+necessities
+
+00:00:18.238 --> 00:00:18.700
+housing
+
+00:00:18.988 --> 00:00:19.375
+food
+
+00:00:19.788 --> 00:00:20.363
+healthcare
+
+00:00:20.675 --> 00:00:21.325
+childcare
+
+00:00:21.550 --> 00:00:22.188
+transport
+
+00:00:22.438 --> 00:00:22.863
+continue
+
+00:00:22.875 --> 00:00:22.962
+to
+
+00:00:22.975 --> 00:00:23.150
+weigh
+
+00:00:23.163 --> 00:00:23.312
+on
+
+00:00:23.325 --> 00:00:23.625
+working
+
+00:00:23.637 --> 00:00:23.925
+class
+
+00:00:23.938 --> 00:00:24.500
+families
+

notebooks/articles/sample.srt

@@ -0,0 +1,161 @@
+WEBVTT
+
+00:00:00.087 --> 00:00:00.762
+Thanksgiving
+
+00:00:00.775 --> 00:00:00.850
+in
+
+00:00:00.863 --> 00:00:01.450
+America
+
+00:00:01.462 --> 00:00:02.438
+2024
+
+00:00:02.975 --> 00:00:03.350
+Social
+
+00:00:03.362 --> 00:00:04.013
+devastation
+
+00:00:04.025 --> 00:00:04.138
+for
+
+00:00:04.150 --> 00:00:04.250
+the
+
+00:00:04.263 --> 00:00:04.650
+working
+
+00:00:04.662 --> 00:00:05.162
+class
+
+00:00:05.475 --> 00:00:05.938
+billions
+
+00:00:05.950 --> 00:00:06.225
+more
+
+00:00:06.237 --> 00:00:06.362
+for
+
+00:00:06.375 --> 00:00:06.475
+the
+
+00:00:06.487 --> 00:00:07.200
+oligarchs
+
+00:00:07.612 --> 00:00:07.750
+By
+
+00:00:07.763 --> 00:00:08.113
+Barry
+
+00:00:08.125 --> 00:00:08.550
+Grey
+
+00:00:08.950 --> 00:00:09.075
+On
+
+00:00:09.088 --> 00:00:09.700
+Thanksgiving
+
+00:00:09.713 --> 00:00:09.975
+Day
+
+00:00:09.988 --> 00:00:10.963
+2024
+
+00:00:11.325 --> 00:00:11.425
+the
+
+00:00:11.438 --> 00:00:11.812
+broad
+
+00:00:11.825 --> 00:00:12.200
+mass
+
+00:00:12.213 --> 00:00:12.287
+of
+
+00:00:12.300 --> 00:00:12.387
+the
+
+00:00:12.400 --> 00:00:12.863
+American
+
+00:00:12.875 --> 00:00:13.575
+population
+
+00:00:13.588 --> 00:00:13.812
+has
+
+00:00:13.825 --> 00:00:14.300
+precious
+
+00:00:14.312 --> 00:00:14.550
+little
+
+00:00:14.562 --> 00:00:14.625
+to
+
+00:00:14.637 --> 00:00:14.775
+be
+
+00:00:14.787 --> 00:00:15.262
+thankful
+
+00:00:15.275 --> 00:00:15.700
+for
+
+00:00:16.100 --> 00:00:16.562
+Inflated
+
+00:00:16.575 --> 00:00:16.925
+costs
+
+00:00:16.938 --> 00:00:17.125
+for
+
+00:00:17.137 --> 00:00:17.288
+all
+
+00:00:17.300 --> 00:00:18.000
+necessities
+
+00:00:18.312 --> 00:00:18.775
+housing
+
+00:00:19.062 --> 00:00:19.450
+food
+
+00:00:19.863 --> 00:00:20.438
+healthcare
+
+00:00:20.750 --> 00:00:21.400
+childcare
+
+00:00:21.625 --> 00:00:22.262
+transport
+
+00:00:22.512 --> 00:00:22.938
+continue
+
+00:00:22.950 --> 00:00:23.038
+to
+
+00:00:23.050 --> 00:00:23.225
+weigh
+
+00:00:23.238 --> 00:00:23.387
+on
+
+00:00:23.400 --> 00:00:23.700
+working
+
+00:00:23.712 --> 00:00:24.000
+class
+
+00:00:24.012 --> 00:00:24.575
+families
+

notebooks/articles/sample.txt

@@ -0,0 +1,5 @@
+# Thanksgiving in America 2024: Social devastation for the working class, billions more for the oligarchs.
+
+## By Barry Grey.
+
+On Thanksgiving Day 2024, the broad mass of the American population has precious little to be thankful for. Inflated costs for all necessities—housing, food, healthcare, childcare, transport—continue to weigh on working class families.

notebooks/articles/slci-n28.html

@@ -0,0 +1 @@
+<p>On Thanksgiving Day 2024, the broad mass of the American population has precious little to be thankful for. Inflated costs for all necessities—housing, food, healthcare, childcare, transport—continue to weigh on working class families. Workers are struggling to scrape together turkey dinners for their families and friends under conditions where the cost of a Thanksgiving meal is up 19 percent from pre-pandemic 2019, according to the American Farm Bureau Federation.</p><placeholder type="media" link="workspace://SpacesStore/3e30b341-71f3-4c36-9233-c61c84aadffd" caption="" usecaption="false"><p></p></placeholder><p>But there is an entirely different reality in the environs of the rich and the super-rich. Champagne glasses are clinking on Wall Street, at Donald Trump’s Mar-a-Lago estate, at the White House and on Capitol Hill as the stock market booms and the bonanza reaped by America’s oligarchs and their political servants under Joe Biden is set to be massively amplified under the incoming Trump administration.</p><p>Outgoing President Biden is spending his holiday at the Nantucket home of David Rubenstein, billionaire co-founder of the Carlyle Group. Defeated presidential candidate Kamala Harris is sunning herself in Hawaii. Most of their voters, and most of Trump’s, are struggling simply to get by.</p><placeholder type="media" link="workspace://SpacesStore/ecbc31ef-0c60-4801-aa23-94881b78ed75" caption="" usecaption="false"><p></p></placeholder><p>The ranks of America’s billionaires grew to 800 under Biden and their collective wealth increased by 62 percent to more than $6.2 trillion (not counting the additional hundreds of billions amassed in the stock market surge since the election of Trump). As of December of last year, the top 1 percent of Americans took 21 percent of all personal incomes, more than double the share of the bottom 50 percent. The top one percent of Americans owned 35 percent of all personal wealth and the top 10 percent owned 71 percent, while the bottom 50 percent owned just 1 percent.</p><p>In less than eight weeks, Trump’s cabal of billionaires, fascists and quacks is set to take office. It will seek to impose an agenda of mass deportations and state repression, escalation of war and genocide, further tax cuts for the rich, the ripping up of what remains of the social safety net, the dismantling of public health and public education, and the lifting of virtually all regulations on big business. Things could not appear rosier for the financial parasites who control both parties and the entire political system.</p><p>Elon Musk, Trump’s crony and the richest man in the world, with a fortune of $300 billion and counting, will be joined by fellow billionaire Vivek Ramaswamy at the head of Trump’s new Department of Government Efficiency, where they plan to cut the federal budget by $2 trillion. This will mean the gutting of Medicare, Medicaid and Social Security and the firing of hundreds of thousands of government workers.</p><placeholder type="media" link="workspace://SpacesStore/fc2d9e86-3aa0-46ea-ba9a-ee36a205513e" caption="" usecaption="false"><p></p></placeholder><p>This is on top of an already unfolding social disaster for the masses. Almost 40 percent of Americans, in a survey by the Harris Poll for Bloomberg News in December of 2023, said their household recently relied on extra money besides their regular income<strong><em> </em></strong>to make ends meet. Of those, 38 percent said the additional amounts barely covered their monthly expenses with nothing left over, and 23 per cent said it wasn’t enough to pay their bills.</p><p>Since last December, mass layoffs in auto, aerospace, retail and other sectors have continued to spread, further devastating working class families. These conditions have already sparked a wave of strikes—at Boeing, on the docks, in the auto sector—in which workers rebelled against the union bureaucrats and voted down sellout contracts.</p><p>Here are some key indices of the social reality confronting broad layers of the American people on Thanksgiving Day:</p><h4>Hunger</h4><ul><li>According to the most recent Census Bureau Household Pulse Survey (October 2023), one out of every eight American adults is struggling to afford enough food. Nearly 28 million adults nationwide—12.5 percent of the adult population—are living in homes where there is either sometimes or often not enough to eat. This is the highest that figure has reached since the first year of the COVID-19 pandemic.</li></ul><h4>Homelessness</h4><p>The “State of Homelessness” document of the National Alliance to End Homelessness, 2024 edition, reports:</p><ul><li>In 2023, the year-over-year increase in the number of people experiencing homelessness was 12.1 percent, the biggest increase since data collection began in 2007.</li><li>From 2022 to 2023, homelessness for entire families increased by 15.5 percent.</li><li>More people than ever are experiencing homelessness for the first time.<strong> </strong>From 2019 to 2023, the number of people who entered emergency shelter for the first time increased more than 23 percent. Over the course of 2023, nearly one million people experienced homelessness for the first time.</li><li>Severe housing cost burdens are on the rise. The number of renter households paying more than 50 percent of their income on rent increased dramatically, rising over 12.6 percent between 2015 and 2022.</li><li>More than half of people experiencing sheltered homelessness, and slightly less than half of people experiencing unsheltered homelessness are formally employed.</li></ul><h4>Poverty</h4><ul><li>According to the Organization for Economic Cooperation and Development (OECD), the United States has the highest poverty rate among the world’s 26 most developed countries. The United Nations Children’s Fund (UNICEF) ranks the United States second behind Mexico on a scale of what economists call “relative child poverty” when measured against 35 of the world’s richest nations.</li><li>In 2023, the official US poverty rate, according to the United States Census Bureau, was 11.1 percent. There were 36.8 million people in poverty in 2023. </li></ul><h4>Life expectancy</h4><ul><li>Overall life expectancy in the US was 76.4 years as of early 2023, the lowest in over 20 years.</li></ul><p>How is this possible in the richest country in the world? The answer is capitalism. This is a system in which the working class, which produces all of the wealth, is systematically robbed of the vast portion of what it produces on the basis of private ownership of the means of production, production for profit, and the historically outmoded nation-state framework of economic life.<strong> </strong></p><p>The levels of oligarchic excess and parasitism in the US are particularly grotesque due to the complete political subordination of the working class to the ruling elite by means of the two-party system. The exclusion of the working class from political life is enforced by the union bureaucracy and its pseudo-left hangers on in such pro-Democratic groups as the Democratic Socialists of America (DSA).</p><p>This is reflected in such facts as a federal minimum wage that remains at $7.25 an hour, not even sufficient to sustain human life. Meanwhile, the two-party monopoly spends a trillion dollars a year on war and the military and a trillion a year to service a national debt of $34 trillion and rising. The latter payouts, which directly enrich the banks and hedge funds, are on top of a combined $12 trillion doled out to rescue the financial elite in the Wall Street crises of 2008 and 2020.</p><p>The millions of workers who voted for Trump did so as a protest against the undisguised indifference of Biden and Harris to the devastating impact of inflation and austerity, including the purging of 40 million people from the Medicaid rolls. They did not vote for dictatorship, the rounding up of immigrant workers in concentration camps policed by the military for summary deportation, the expansion of US imperialism’s global war to China, an increase in Washington’s support for the genocide in Gaza, or the destruction of millions more jobs and basic social services.</p><p>They will be stunned and enraged by what is coming under Trump, and they will resist, massively and on a revolutionary scale. Leon Trotsky in his monumental <em>History of the Russian Revolution </em>devoted a chapter to “The Tzar and the Tzarina,” in which he wrote of the cognitive blindness that seems to possess ruling classes on the eve of revolutionary upheavals. He wrote:</p><blockquote><p>To that historic flood which was rolling its billows each one closer to the gates of his palace, the last Romanov opposed only a dumb indifference. It seemed as though between his consciousness and his epoch there stood some transparent but absolutely impenetrable medium.</p></blockquote><p>Trotsky continued:</p><blockquote><p>The tzar had no need of narcotics: the fatal “dope” was in his blood. Its symptoms merely seemed especially striking on the background of those great events of war and domestic crisis which led up to the revolution.</p></blockquote><p>The American ruling class is facing a historical reckoning. The social force that alone can stop and reverse the slide to fascism and world war is the working class, in the US and internationally. It will fight, but it requires a scientific Marxist and internationalist perspective and strategy and the building of a new leadership, which can be accomplished only by the Trotskyist movement, the Socialist Equality Party and the International Committee of the Fourth International. To all those who see the dangers and want to fight, we say join the SEP and take up the fight for the political independence of the working class and socialism!</p>

notebooks/articles/slci-n28.md

@@ -0,0 +1,58 @@
+On Thanksgiving Day 2024, the broad mass of the American population has precious little to be thankful for. Inflated costs for all necessities—housing, food, healthcare, childcare, transport—continue to weigh on working class families. Workers are struggling to scrape together turkey dinners for their families and friends under conditions where the cost of a Thanksgiving meal is up 19 percent from pre-pandemic 2019, according to the American Farm Bureau Federation.
+
+But there is an entirely different reality in the environs of the rich and the super-rich. Champagne glasses are clinking on Wall Street, at Donald Trump’s Mar-a-Lago estate, at the White House and on Capitol Hill as the stock market booms and the bonanza reaped by America’s oligarchs and their political servants under Joe Biden is set to be massively amplified under the incoming Trump administration.
+
+Outgoing President Biden is spending his holiday at the Nantucket home of David Rubenstein, billionaire co-founder of the Carlyle Group. Defeated presidential candidate Kamala Harris is sunning herself in Hawaii. Most of their voters, and most of Trump’s, are struggling simply to get by.
+
+The ranks of America’s billionaires grew to 800 under Biden and their collective wealth increased by 62 percent to more than \$6.2 trillion (not counting the additional hundreds of billions amassed in the stock market surge since the election of Trump). As of December of last year, the top 1 percent of Americans took 21 percent of all personal incomes, more than double the share of the bottom 50 percent. The top one percent of Americans owned 35 percent of all personal wealth and the top 10 percent owned 71 percent, while the bottom 50 percent owned just 1 percent.
+
+In less than eight weeks, Trump’s cabal of billionaires, fascists and quacks is set to take office. It will seek to impose an agenda of mass deportations and state repression, escalation of war and genocide, further tax cuts for the rich, the ripping up of what remains of the social safety net, the dismantling of public health and public education, and the lifting of virtually all regulations on big business. Things could not appear rosier for the financial parasites who control both parties and the entire political system.
+
+Elon Musk, Trump’s crony and the richest man in the world, with a fortune of \$300 billion and counting, will be joined by fellow billionaire Vivek Ramaswamy at the head of Trump’s new Department of Government Efficiency, where they plan to cut the federal budget by \$2 trillion. This will mean the gutting of Medicare, Medicaid and Social Security and the firing of hundreds of thousands of government workers.
+
+This is on top of an already unfolding social disaster for the masses. Almost 40 percent of Americans, in a survey by the Harris Poll for Bloomberg News in December of 2023, said their household recently relied on extra money besides their regular income **** to make ends meet. Of those, 38 percent said the additional amounts barely covered their monthly expenses with nothing left over, and 23 per cent said it wasn’t enough to pay their bills.
+
+Since last December, mass layoffs in auto, aerospace, retail and other sectors have continued to spread, further devastating working class families. These conditions have already sparked a wave of strikes—at Boeing, on the docks, in the auto sector—in which workers rebelled against the union bureaucrats and voted down sellout contracts.
+
+Here are some key indices of the social reality confronting broad layers of the American people on Thanksgiving Day:
+
+#### Hunger
+
+-   According to the most recent Census Bureau Household Pulse Survey (October 2023), one out of every eight American adults is struggling to afford enough food. Nearly 28 million adults nationwide—12.5 percent of the adult population—are living in homes where there is either sometimes or often not enough to eat. This is the highest that figure has reached since the first year of the COVID-19 pandemic.
+
+#### Homelessness
+
+The “State of Homelessness” document of the National Alliance to End Homelessness, 2024 edition, reports:
+
+-   In 2023, the year-over-year increase in the number of people experiencing homelessness was 12.1 percent, the biggest increase since data collection began in 2007.
+-   From 2022 to 2023, homelessness for entire families increased by 15.5 percent.
+-   More people than ever are experiencing homelessness for the first time. From 2019 to 2023, the number of people who entered emergency shelter for the first time increased more than 23 percent. Over the course of 2023, nearly one million people experienced homelessness for the first time.
+-   Severe housing cost burdens are on the rise. The number of renter households paying more than 50 percent of their income on rent increased dramatically, rising over 12.6 percent between 2015 and 2022.
+-   More than half of people experiencing sheltered homelessness, and slightly less than half of people experiencing unsheltered homelessness are formally employed.
+
+#### Poverty
+
+-   According to the Organization for Economic Cooperation and Development (OECD), the United States has the highest poverty rate among the world’s 26 most developed countries. The United Nations Children’s Fund (UNICEF) ranks the United States second behind Mexico on a scale of what economists call “relative child poverty” when measured against 35 of the world’s richest nations.
+-   In 2023, the official US poverty rate, according to the United States Census Bureau, was 11.1 percent. There were 36.8 million people in poverty in 2023.
+
+#### Life expectancy
+
+-   Overall life expectancy in the US was 76.4 years as of early 2023, the lowest in over 20 years.
+
+How is this possible in the richest country in the world? The answer is capitalism. This is a system in which the working class, which produces all of the wealth, is systematically robbed of the vast portion of what it produces on the basis of private ownership of the means of production, production for profit, and the historically outmoded nation-state framework of economic life.
+
+The levels of oligarchic excess and parasitism in the US are particularly grotesque due to the complete political subordination of the working class to the ruling elite by means of the two-party system. The exclusion of the working class from political life is enforced by the union bureaucracy and its pseudo-left hangers on in such pro-Democratic groups as the Democratic Socialists of America (DSA).
+
+This is reflected in such facts as a federal minimum wage that remains at \$7.25 an hour, not even sufficient to sustain human life. Meanwhile, the two-party monopoly spends a trillion dollars a year on war and the military and a trillion a year to service a national debt of \$34 trillion and rising. The latter payouts, which directly enrich the banks and hedge funds, are on top of a combined \$12 trillion doled out to rescue the financial elite in the Wall Street crises of 2008 and 2020.
+
+The millions of workers who voted for Trump did so as a protest against the undisguised indifference of Biden and Harris to the devastating impact of inflation and austerity, including the purging of 40 million people from the Medicaid rolls. They did not vote for dictatorship, the rounding up of immigrant workers in concentration camps policed by the military for summary deportation, the expansion of US imperialism’s global war to China, an increase in Washington’s support for the genocide in Gaza, or the destruction of millions more jobs and basic social services.
+
+They will be stunned and enraged by what is coming under Trump, and they will resist, massively and on a revolutionary scale. Leon Trotsky in his monumental *History of the Russian Revolution* devoted a chapter to “The Tzar and the Tzarina,” in which he wrote of the cognitive blindness that seems to possess ruling classes on the eve of revolutionary upheavals. He wrote:
+
+> To that historic flood which was rolling its billows each one closer to the gates of his palace, the last Romanov opposed only a dumb indifference. It seemed as though between his consciousness and his epoch there stood some transparent but absolutely impenetrable medium.
+
+Trotsky continued:
+
+> The tzar had no need of narcotics: the fatal “dope” was in his blood. Its symptoms merely seemed especially striking on the background of those great events of war and domestic crisis which led up to the revolution.
+
+The American ruling class is facing a historical reckoning. The social force that alone can stop and reverse the slide to fascism and world war is the working class, in the US and internationally. It will fight, but it requires a scientific Marxist and internationalist perspective and strategy and the building of a new leadership, which can be accomplished only by the Trotskyist movement, the Socialist Equality Party and the International Committee of the Fourth International. To all those who see the dangers and want to fight, we say join the SEP and take up the fight for the political independence of the working class and socialism!

notebooks/articles/slci-n28.txt

@@ -0,0 +1,58 @@
+On Thanksgiving Day 2024, the broad mass of the American population has precious little to be thankful for. Inflated costs for all necessities—housing, food, healthcare, childcare, transport—continue to weigh on working class families. Workers are struggling to scrape together turkey dinners for their families and friends under conditions where the cost of a Thanksgiving meal is up 19 percent from pre-pandemic 2019, according to the American Farm Bureau Federation.
+
+But there is an entirely different reality in the environs of the rich and the super-rich. Champagne glasses are clinking on Wall Street, at Donald Trump’s Mar-a-Lago estate, at the White House and on Capitol Hill as the stock market booms and the bonanza reaped by America’s oligarchs and their political servants under Joe Biden is set to be massively amplified under the incoming Trump administration.
+
+Outgoing President Biden is spending his holiday at the Nantucket home of David Rubenstein, billionaire co-founder of the Carlyle Group. Defeated presidential candidate Kamala Harris is sunning herself in Hawaii. Most of their voters, and most of Trump’s, are struggling simply to get by.
+
+The ranks of America’s billionaires grew to 800 under Biden and their collective wealth increased by 62 percent to more than $6.2 trillion (not counting the additional hundreds of billions amassed in the stock market surge since the election of Trump). As of December of last year, the top 1 percent of Americans took 21 percent of all personal incomes, more than double the share of the bottom 50 percent. The top one percent of Americans owned 35 percent of all personal wealth and the top 10 percent owned 71 percent, while the bottom 50 percent owned just 1 percent.
+
+In less than eight weeks, Trump’s cabal of billionaires, fascists and quacks is set to take office. It will seek to impose an agenda of mass deportations and state repression, escalation of war and genocide, further tax cuts for the rich, the ripping up of what remains of the social safety net, the dismantling of public health and public education, and the lifting of virtually all regulations on big business. Things could not appear rosier for the financial parasites who control both parties and the entire political system.
+
+Elon Musk, Trump’s crony and the richest man in the world, with a fortune of $300 billion and counting, will be joined by fellow billionaire Vivek Ramaswamy at the head of Trump’s new Department of Government Efficiency, where they plan to cut the federal budget by $2 trillion. This will mean the gutting of Medicare, Medicaid and Social Security and the firing of hundreds of thousands of government workers.
+
+This is on top of an already unfolding social disaster for the masses. Almost 40 percent of Americans, in a survey by the Harris Poll for Bloomberg News in December of 2023, said their household recently relied on extra money besides their regular income to make ends meet. Of those, 38 percent said the additional amounts barely covered their monthly expenses with nothing left over, and 23 per cent said it wasn’t enough to pay their bills.
+
+Since last December, mass layoffs in auto, aerospace, retail and other sectors have continued to spread, further devastating working class families. These conditions have already sparked a wave of strikes—at Boeing, on the docks, in the auto sector—in which workers rebelled against the union bureaucrats and voted down sellout contracts.
+
+Here are some key indices of the social reality confronting broad layers of the American people on Thanksgiving Day:
+
+Hunger
+
+-   According to the most recent Census Bureau Household Pulse Survey (October 2023), one out of every eight American adults is struggling to afford enough food. Nearly 28 million adults nationwide—12.5 percent of the adult population—are living in homes where there is either sometimes or often not enough to eat. This is the highest that figure has reached since the first year of the COVID-19 pandemic.
+
+Homelessness
+
+The “State of Homelessness” document of the National Alliance to End Homelessness, 2024 edition, reports:
+
+-   In 2023, the year-over-year increase in the number of people experiencing homelessness was 12.1 percent, the biggest increase since data collection began in 2007.
+-   From 2022 to 2023, homelessness for entire families increased by 15.5 percent.
+-   More people than ever are experiencing homelessness for the first time. From 2019 to 2023, the number of people who entered emergency shelter for the first time increased more than 23 percent. Over the course of 2023, nearly one million people experienced homelessness for the first time.
+-   Severe housing cost burdens are on the rise. The number of renter households paying more than 50 percent of their income on rent increased dramatically, rising over 12.6 percent between 2015 and 2022.
+-   More than half of people experiencing sheltered homelessness, and slightly less than half of people experiencing unsheltered homelessness are formally employed.
+
+Poverty
+
+-   According to the Organization for Economic Cooperation and Development (OECD), the United States has the highest poverty rate among the world’s 26 most developed countries. The United Nations Children’s Fund (UNICEF) ranks the United States second behind Mexico on a scale of what economists call “relative child poverty” when measured against 35 of the world’s richest nations.
+-   In 2023, the official US poverty rate, according to the United States Census Bureau, was 11.1 percent. There were 36.8 million people in poverty in 2023.
+
+Life expectancy
+
+-   Overall life expectancy in the US was 76.4 years as of early 2023, the lowest in over 20 years.
+
+How is this possible in the richest country in the world? The answer is capitalism. This is a system in which the working class, which produces all of the wealth, is systematically robbed of the vast portion of what it produces on the basis of private ownership of the means of production, production for profit, and the historically outmoded nation-state framework of economic life.
+
+The levels of oligarchic excess and parasitism in the US are particularly grotesque due to the complete political subordination of the working class to the ruling elite by means of the two-party system. The exclusion of the working class from political life is enforced by the union bureaucracy and its pseudo-left hangers on in such pro-Democratic groups as the Democratic Socialists of America (DSA).
+
+This is reflected in such facts as a federal minimum wage that remains at $7.25 an hour, not even sufficient to sustain human life. Meanwhile, the two-party monopoly spends a trillion dollars a year on war and the military and a trillion a year to service a national debt of $34 trillion and rising. The latter payouts, which directly enrich the banks and hedge funds, are on top of a combined $12 trillion doled out to rescue the financial elite in the Wall Street crises of 2008 and 2020.
+
+The millions of workers who voted for Trump did so as a protest against the undisguised indifference of Biden and Harris to the devastating impact of inflation and austerity, including the purging of 40 million people from the Medicaid rolls. They did not vote for dictatorship, the rounding up of immigrant workers in concentration camps policed by the military for summary deportation, the expansion of US imperialism’s global war to China, an increase in Washington’s support for the genocide in Gaza, or the destruction of millions more jobs and basic social services.
+
+They will be stunned and enraged by what is coming under Trump, and they will resist, massively and on a revolutionary scale. Leon Trotsky in his monumental History of the Russian Revolution devoted a chapter to “The Tzar and the Tzarina,” in which he wrote of the cognitive blindness that seems to possess ruling classes on the eve of revolutionary upheavals. He wrote:
+
+  To that historic flood which was rolling its billows each one closer to the gates of his palace, the last Romanov opposed only a dumb indifference. It seemed as though between his consciousness and his epoch there stood some transparent but absolutely impenetrable medium.
+
+Trotsky continued:
+
+  The tzar had no need of narcotics: the fatal “dope” was in his blood. Its symptoms merely seemed especially striking on the background of those great events of war and domestic crisis which led up to the revolution.
+
+The American ruling class is facing a historical reckoning. The social force that alone can stop and reverse the slide to fascism and world war is the working class, in the US and internationally. It will fight, but it requires a scientific Marxist and internationalist perspective and strategy and the building of a new leadership, which can be accomplished only by the Trotskyist movement, the Socialist Equality Party and the International Committee of the Fourth International. To all those who see the dangers and want to fight, we say join the SEP and take up the fight for the political independence of the working class and socialism!

notebooks/couchdb.http

@@ -0,0 +1,59 @@
+@url = {{$dotenv COUCHDB_URL}}
+@user = {{$dotenv COUCHDB_USER}}
+@password = {{$dotenv COUCHDB_PASSWORD}}
+@db = {{$dotenv COUCHDB_DB}}
+@origin = 0
+@origin = 316723-g1AAAACReJzLYWBgYMpgTmHgzcvPy09JdcjLz8gvLskBCScyJNX___8_K4M5iYEpWyEXKMaekpyabGBuiK4ehwl5LECSoQFI_YcblCUMNsgsMS010dQSXVsWAD8FLCA
+@batchSize = 10
+@includeDocs = true
+@authHeader = Authorization: Basic {{user}}:{{password}}
+
+###
+# @name session
+POST {{url}}/_session
+Content-Type: application/json
+
+{
+    "name": "{{user}}",
+    "password": "{{password}}"
+}
+
+###
+# @name docById
+@id = b7fdc644-5b24-40ae-b489-37b3fc0c5541
+GET {{url}}/{{db}}/{{id}}
+{{authHeader}}
+
+###
+# @name designDocs
+GET {{url}}/{{db}}/_design_docs
+{{authHeader}}
+
+###
+# @name design
+GET {{url}}/{{db}}/_design/wsws/_view/by_path
+    ?limit=1
+    &key="/en/articles/2024/11/28/slci-n28.html"
+    &include_docs=true
+{{authHeader}}
+
+###
+# @name changes
+GET {{url}}/{{db}}/_changes
+    ?limit={{batchSize}}
+    &include_docs={{includeDocs}}
+    &since={{origin}}
+
+###
+# @name changes
+GET {{url}}/{{db}}/_changes
+    ?limit={{batchSize}}
+    &include_docs={{includeDocs}}
+    &since={{changes.response.body.last_seq}}
+
+###
+# @name broken
+GET {{url}}/{{db}}/_changes
+    ?limit=10
+    &include_docs=true
+    &since=316731-g1AAAACReJzLYWBgYMpgTmHgzcvPy09JdcjLz8gvLskBCScyJNX___8_K4M5iYEpWyEXKMaekpyabGBuiK4ehwl5LECSoQFI_YcblCUNNsgsMS010dQSXVsWAD_1LCg

notebooks/sample.txt

@@ -0,0 +1,34 @@
+Thanksgiving in America 2024: Social devastation for the working class, billions more for the oligarchs
+By Barry Grey
+On Thanksgiving Day 2024, the broad mass of the American population has precious little to be thankful for. Inflated costs for all necessities---housing, food, healthcare, childcare, transport---continue to weigh on working class families. Workers are struggling to scrape together turkey dinners for their families and friends under conditions where the cost of a Thanksgiving meal is up 19 percent from pre-pandemic 2019, according to the American Farm Bureau Federation.
+But there is an entirely different reality in the environs of the rich and the super-rich. Champagne glasses are clinking on Wall Street, at Donald Trump's Mar-a-Lago estate, at the White House and on Capitol Hill as the stock market booms and the bonanza reaped by America's oligarchs and their political servants under Joe Biden is set to be massively amplified under the incoming Trump administration.
+Outgoing President Biden is spending his holiday at the Nantucket home of David Rubenstein, billionaire co-founder of the Carlyle Group. Defeated presidential candidate Kamala Harris is sunning herself in Hawaii. Most of their voters, and most of Trump's, are struggling simply to get by.
+The ranks of America's billionaires grew to 800 under Biden and their collective wealth increased by 62 percent to more than $6.2 trillion (not counting the additional hundreds of billions amassed in the stock market surge since the election of Trump). As of December of last year, the top 1 percent of Americans took 21 percent of all personal incomes, more than double the share of the bottom 50 percent. The top one percent of Americans owned 35 percent of all personal wealth and the top 10 percent owned 71 percent, while the bottom 50 percent owned just 1 percent.
+In less than eight weeks, Trump's cabal of billionaires, fascists and quacks is set to take office. It will seek to impose an agenda of mass deportations and state repression, escalation of war and genocide, further tax cuts for the rich, the ripping up of what remains of the social safety net, the dismantling of public health and public education, and the lifting of virtually all regulations on big business. Things could not appear rosier for the financial parasites who control both parties and the entire political system.
+Elon Musk, Trump's crony and the richest man in the world, with a fortune of $300 billion and counting, will be joined by fellow billionaire Vivek Ramaswamy at the head of Trump's new Department of Government Efficiency, where they plan to cut the federal budget by $2 trillion. This will mean the gutting of Medicare, Medicaid and Social Security and the firing of hundreds of thousands of government workers.
+This is on top of an already unfolding social disaster for the masses. Almost 40 percent of Americans, in a survey by the Harris Poll for Bloomberg News in December of 2023, said their household recently relied on extra money besides their regular income **** to make ends meet. Of those, 38 percent said the additional amounts barely covered their monthly expenses with nothing left over, and 23 per cent said it wasn't enough to pay their bills.
+Since last December, mass layoffs in auto, aerospace, retail and other sectors have continued to spread, further devastating working class families. These conditions have already sparked a wave of strikes---at Boeing, on the docks, in the auto sector---in which workers rebelled against the union bureaucrats and voted down sellout contracts.
+Here are some key indices of the social reality confronting broad layers of the American people on Thanksgiving Day:
+Hunger
+According to the most recent Census Bureau Household Pulse Survey (October 2023), one out of every eight American adults is struggling to afford enough food. Nearly 28 million adults nationwide---12.5 percent of the adult population---are living in homes where there is either sometimes or often not enough to eat. This is the highest that figure has reached since the first year of the COVID-19 pandemic.
+Homelessness
+The "State of Homelessness" document of the National Alliance to End Homelessness, 2024 edition, reports:
+In 2023, the year-over-year increase in the number of people experiencing homelessness was 12.1 percent, the biggest increase since data collection began in 2007.
+From 2022 to 2023, homelessness for entire families increased by 15.5 percent.
+More people than ever are experiencing homelessness for the first time. From 2019 to 2023, the number of people who entered emergency shelter for the first time increased more than 23 percent. Over the course of 2023, nearly one million people experienced homelessness for the first time.
+Severe housing cost burdens are on the rise. The number of renter households paying more than 50 percent of their income on rent increased dramatically, rising over 12.6 percent between 2015 and 2022.
+More than half of people experiencing sheltered homelessness, and slightly less than half of people experiencing unsheltered homelessness are formally employed.
+Poverty
+According to the Organization for Economic Cooperation and Development (OECD), the United States has the highest poverty rate among the world's 26 most developed countries. The United Nations Children's Fund (UNICEF) ranks the United States second behind Mexico on a scale of what economists call "relative child poverty" when measured against 35 of the world's richest nations.
+In 2023, the official US poverty rate, according to the United States Census Bureau, was 11.1 percent. There were 36.8 million people in poverty in 2023.
+Life expectancy
+Overall life expectancy in the US was 76.4 years as of early 2023, the lowest in over 20 years.
+How is this possible in the richest country in the world? The answer is capitalism. This is a system in which the working class, which produces all of the wealth, is systematically robbed of the vast portion of what it produces on the basis of private ownership of the means of production, production for profit, and the historically outmoded nation-state framework of economic life.
+The levels of oligarchic excess and parasitism in the US are particularly grotesque due to the complete political subordination of the working class to the ruling elite by means of the two-party system. The exclusion of the working class from political life is enforced by the union bureaucracy and its pseudo-left hangers on in such pro-Democratic groups as the Democratic Socialists of America (DSA).
+This is reflected in such facts as a federal minimum wage that remains at $7.25 an hour, not even sufficient to sustain human life. Meanwhile, the two-party monopoly spends a trillion dollars a year on war and the military and a trillion a year to service a national debt of $34 trillion and rising. The latter payouts, which directly enrich the banks and hedge funds, are on top of a combined $12 trillion doled out to rescue the financial elite in the Wall Street crises of 2008 and 2020.
+The millions of workers who voted for Trump did so as a protest against the undisguised indifference of Biden and Harris to the devastating impact of inflation and austerity, including the purging of 40 million people from the Medicaid rolls. They did not vote for dictatorship, the rounding up of immigrant workers in concentration camps policed by the military for summary deportation, the expansion of US imperialism's global war to China, an increase in Washington's support for the genocide in Gaza, or the destruction of millions more jobs and basic social services.
+They will be stunned and enraged by what is coming under Trump, and they will resist, massively and on a revolutionary scale. Leon Trotsky in his monumental History of the Russian Revolution devoted a chapter to "The Tzar and the Tzarina," in which he wrote of the cognitive blindness that seems to possess ruling classes on the eve of revolutionary upheavals. He wrote:
+To that historic flood which was rolling its billows each one closer to the gates of his palace, the last Romanov opposed only a dumb indifference. It seemed as though between his consciousness and his epoch there stood some transparent but absolutely impenetrable medium.
+Trotsky continued:
+The tzar had no need of narcotics: the fatal "dope" was in his blood. Its symptoms merely seemed especially striking on the background of those great events of war and domestic crisis which led up to the revolution.
+The American ruling class is facing a historical reckoning. The social force that alone can stop and reverse the slide to fascism and world war is the working class, in the US and internationally. It will fight, but it requires a scientific Marxist and internationalist perspective and strategy and the building of a new leadership, which can be accomplished only by the Trotskyist movement, the Socialist Equality Party and the International Committee of the Fourth International. To all those who see the dangers and want to fight, we say join the SEP and take up the fight for the political independence of the working class and socialism!

packages.txt

@@ -0,0 +1 @@
+pandoc

poetry.lock

@@ -1847,13 +1847,13 @@ trio = ["trio (>=0.22.0,<1.0)"]
 
 [[package]]
 name = "httpx"
-version = "0.27.2"
+version = "0.28.0"
 description = "The next generation HTTP client."
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "httpx-0.27.2-py3-none-any.whl", hash = "sha256:7bb2708e112d8fdd7829cd4243970f0c223274051cb35ee80c03301ee29a3df0"},
-    {file = "httpx-0.27.2.tar.gz", hash = "sha256:f7c2be1d2f3c3c3160d441802406b206c2b76f5947b11115e6df10c6c65e66c2"},
+    {file = "httpx-0.28.0-py3-none-any.whl", hash = "sha256:dc0b419a0cfeb6e8b34e85167c0da2671206f5095f1baa9663d23bcfd6b535fc"},
+    {file = "httpx-0.28.0.tar.gz", hash = "sha256:0858d3bab51ba7e386637f22a61d8ccddaeec5f3fe4209da3a6168dbb91573e0"},
 ]
 
 [package.dependencies]
@@ -1861,7 +1861,6 @@ anyio = "*"
 certifi = "*"
 httpcore = "==1.*"
 idna = "*"
-sniffio = "*"
 
 [package.extras]
 brotli = ["brotli", "brotlicffi"]
@@ -3420,6 +3419,20 @@ files = [
 numpy = ">=1.23.5"
 types-pytz = ">=2022.1.1"
 
+[[package]]
+name = "pandoc"
+version = "2.4"
+description = "Pandoc Documents for Python"
+optional = false
+python-versions = "*"
+files = [
+    {file = "pandoc-2.4.tar.gz", hash = "sha256:ecd1f8cbb7f4180c6b5db4a17a7c1a74df519995f5f186ef81ce72a9cbd0dd9a"},
+]
+
+[package.dependencies]
+plumbum = "*"
+ply = "*"
+
 [[package]]
 name = "parso"
 version = "0.8.4"
@@ -3676,6 +3689,37 @@ files = [
 dev = ["pre-commit", "tox"]
 testing = ["pytest", "pytest-benchmark"]
 
+[[package]]
+name = "plumbum"
+version = "1.9.0"
+description = "Plumbum: shell combinators library"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "plumbum-1.9.0-py3-none-any.whl", hash = "sha256:9fd0d3b0e8d86e4b581af36edf3f3bbe9d1ae15b45b8caab28de1bcb27aaa7f5"},
+    {file = "plumbum-1.9.0.tar.gz", hash = "sha256:e640062b72642c3873bd5bdc3effed75ba4d3c70ef6b6a7b907357a84d909219"},
+]
+
+[package.dependencies]
+pywin32 = {version = "*", markers = "platform_system == \"Windows\" and platform_python_implementation != \"PyPy\""}
+
+[package.extras]
+dev = ["coverage[toml]", "paramiko", "psutil", "pytest (>=6.0)", "pytest-cov", "pytest-mock", "pytest-timeout"]
+docs = ["sphinx (>=4.0.0)", "sphinx-rtd-theme (>=1.0.0)"]
+ssh = ["paramiko"]
+test = ["coverage[toml]", "paramiko", "psutil", "pytest (>=6.0)", "pytest-cov", "pytest-mock", "pytest-timeout"]
+
+[[package]]
+name = "ply"
+version = "3.11"
+description = "Python Lex & Yacc"
+optional = false
+python-versions = "*"
+files = [
+    {file = "ply-3.11-py2.py3-none-any.whl", hash = "sha256:096f9b8350b65ebd2fd1346b12452efe5b9607f7482813ffca50c22722a807ce"},
+    {file = "ply-3.11.tar.gz", hash = "sha256:00c7c1aaa88358b9c765b6d3000c6eec0ba42abca5351b095321aef446081da3"},
+]
+
 [[package]]
 name = "pooch"
 version = "1.8.2"
@@ -5731,6 +5775,17 @@ files = [
     {file = "types_pytz-2024.2.0.20241003-py3-none-any.whl", hash = "sha256:3e22df1336c0c6ad1d29163c8fda82736909eb977281cb823c57f8bae07118b7"},
 ]
 
+[[package]]
+name = "types-pyyaml"
+version = "6.0.12.20240917"
+description = "Typing stubs for PyYAML"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "types-PyYAML-6.0.12.20240917.tar.gz", hash = "sha256:d1405a86f9576682234ef83bcb4e6fff7c9305c8b1fbad5e0bcd4f7dbdc9c587"},
+    {file = "types_PyYAML-6.0.12.20240917-py3-none-any.whl", hash = "sha256:392b267f1c0fe6022952462bf5d6523f31e37f6cea49b14cee7ad634b6301570"},
+]
+
 [[package]]
 name = "types-regex"
 version = "2024.11.6.20241108"
@@ -6139,4 +6194,4 @@ propcache = ">=0.2.0"
 [metadata]
 lock-version = "2.0"
 python-versions = "~3.10"
-content-hash = "2a4fe2c79fae82f02d2228d746aea2632d6057cdd5685673c9a765856be76291"
+content-hash = "9aec331b8bb3a245ef2f232c85343bc8a1114e5d03679e3309882d59d617e083"

pyproject.toml

@@ -6,7 +6,6 @@ authors = ["Jesus Lopez <jesus@jesusla.com>"]
 readme = "README.md"
 packages = [
     { include = "assets", from = "." },
-    { include = "core", from = "." },
     { include = "rvc", from = "." },
     { include = "tabs", from = "." },
     { include = "tts_service", from = "." },
@@ -49,6 +48,9 @@ tqdm = "^4.67.1"
 transformers = "4.44.2"
 versatile-audio-upscaler = "^0.0.2"
 wget = "^3.2"
+httpx = "^0.28.0"
+pandoc = "^2.4"
+pyyaml = "^6.0.2"
 
 [tool.poetry.group.ci.dependencies]
 gradio = "4.43.0"
@@ -75,6 +77,7 @@ types-boto3 = "^1.0.2"
 types-regex = "^2024.11.6.20241108"
 types-requests = "^2.32.0.20241016"
 types-six = "^1.16.21.20241105"
+types-pyyaml = "^6.0.12.20240917"
 
 
 [tool.ruff]
@@ -99,7 +102,7 @@ select = [
 
 
 [tool.mypy]
-packages = "assets,core,rvc,tabs,tts_service,tests"
+packages = "assets,rvc,tabs,tts_service,tests"
 check_untyped_defs = true
 explicit_package_bases = true
 namespace_packages = true
@@ -150,6 +153,7 @@ module = [
     "local_attention",
     "matplotlib.*",
     "noisereduce",
+    "pandoc",
     "pedalboard_native",
     "pydub",
     "pypresence",

requirements.txt

@@ -582,9 +582,9 @@ h11==0.14.0 ; python_version >= "3.10" and python_version < "3.11" \
 httpcore==1.0.7 ; python_version >= "3.10" and python_version < "3.11" \
     --hash=sha256:8551cb62a169ec7162ac7be8d4817d561f60e08eaa485234898414bb5a8a0b4c \
     --hash=sha256:a3fff8f43dc260d5bd363d9f9cf1830fa3a458b332856f34282de498ed420edd
-httpx==0.27.2 ; python_version >= "3.10" and python_version < "3.11" \
-    --hash=sha256:7bb2708e112d8fdd7829cd4243970f0c223274051cb35ee80c03301ee29a3df0 \
-    --hash=sha256:f7c2be1d2f3c3c3160d441802406b206c2b76f5947b11115e6df10c6c65e66c2
+httpx==0.28.0 ; python_version >= "3.10" and python_version < "3.11" \
+    --hash=sha256:0858d3bab51ba7e386637f22a61d8ccddaeec5f3fe4209da3a6168dbb91573e0 \
+    --hash=sha256:dc0b419a0cfeb6e8b34e85167c0da2671206f5095f1baa9663d23bcfd6b535fc
 huggingface-hub==0.26.2 ; python_version >= "3.10" and python_version < "3.11" \
     --hash=sha256:98c2a5a8e786c7b2cb6fdeb2740893cba4d53e312572ed3d8afafda65b128c46 \
     --hash=sha256:b100d853465d965733964d123939ba287da60a547087783ddff8a323f340332b
@@ -1332,6 +1332,8 @@ pandas==2.2.3 ; python_version >= "3.10" and python_version < "3.11" \
     --hash=sha256:f00d1345d84d8c86a63e476bb4955e46458b304b9575dcf71102b5c705320015 \
     --hash=sha256:f3a255b2c19987fbbe62a9dfd6cff7ff2aa9ccab3fc75218fd4b7530f01efa24 \
     --hash=sha256:fffb8ae78d8af97f849404f21411c95062db1496aeb3e56f146f0355c9989319
+pandoc==2.4 ; python_version >= "3.10" and python_version < "3.11" \
+    --hash=sha256:ecd1f8cbb7f4180c6b5db4a17a7c1a74df519995f5f186ef81ce72a9cbd0dd9a
 pedalboard==0.9.16 ; python_version >= "3.10" and python_version < "3.11" \
     --hash=sha256:031e6833c5983c3fe0a96bc4ff04790663a9e95a01c402828bd5a4eff4b8b541 \
     --hash=sha256:03e73da46d6678a8adbd1ebc70bf38e4316918e44514eb9b1d7989bfb43cb30c \
@@ -1455,6 +1457,12 @@ pillow==10.4.0 ; python_version >= "3.10" and python_version < "3.11" \
 platformdirs==4.3.6 ; python_version >= "3.10" and python_version < "3.11" \
     --hash=sha256:357fb2acbc885b0419afd3ce3ed34564c13c9b95c89360cd9563f73aa5e2b907 \
     --hash=sha256:73e575e1408ab8103900836b97580d5307456908a03e92031bab39e4554cc3fb
+plumbum==1.9.0 ; python_version >= "3.10" and python_version < "3.11" \
+    --hash=sha256:9fd0d3b0e8d86e4b581af36edf3f3bbe9d1ae15b45b8caab28de1bcb27aaa7f5 \
+    --hash=sha256:e640062b72642c3873bd5bdc3effed75ba4d3c70ef6b6a7b907357a84d909219
+ply==3.11 ; python_version >= "3.10" and python_version < "3.11" \
+    --hash=sha256:00c7c1aaa88358b9c765b6d3000c6eec0ba42abca5351b095321aef446081da3 \
+    --hash=sha256:096f9b8350b65ebd2fd1346b12452efe5b9607f7482813ffca50c22722a807ce
 pooch==1.8.2 ; python_version >= "3.10" and python_version < "3.11" \
     --hash=sha256:3529a57096f7198778a5ceefd5ac3ef0e4d06a6ddaf9fc2d609b806f25302c47 \
     --hash=sha256:76561f0de68a01da4df6af38e9955c4c9d1a5c90da73f7e40276a5728ec83d10
@@ -1689,6 +1697,25 @@ python-multipart==0.0.17 ; python_version >= "3.10" and python_version < "3.11"
 pytz==2024.2 ; python_version >= "3.10" and python_version < "3.11" \
     --hash=sha256:2aa355083c50a0f93fa581709deac0c9ad65cca8a9e9beac660adcbd493c798a \
     --hash=sha256:31c7c1817eb7fae7ca4b8c7ee50c72f93aa2dd863de768e1ef4245d426aa0725
+pywin32==308 ; platform_system == "Windows" and platform_python_implementation != "PyPy" and python_version >= "3.10" and python_version < "3.11" \
+    --hash=sha256:00b3e11ef09ede56c6a43c71f2d31857cf7c54b0ab6e78ac659497abd2834f47 \
+    --hash=sha256:100a5442b7332070983c4cd03f2e906a5648a5104b8a7f50175f7906efd16bb6 \
+    --hash=sha256:13dcb914ed4347019fbec6697a01a0aec61019c1046c2b905410d197856326a6 \
+    --hash=sha256:1c44539a37a5b7b21d02ab34e6a4d314e0788f1690d65b48e9b0b89f31abbbed \
+    --hash=sha256:1f696ab352a2ddd63bd07430080dd598e6369152ea13a25ebcdd2f503a38f1ff \
+    --hash=sha256:3b92622e29d651c6b783e368ba7d6722b1634b8e70bd376fd7610fe1992e19de \
+    --hash=sha256:4fc888c59b3c0bef905ce7eb7e2106a07712015ea1c8234b703a088d46110e8e \
+    --hash=sha256:575621b90f0dc2695fec346b2d6302faebd4f0f45c05ea29404cefe35d89442b \
+    --hash=sha256:5794e764ebcabf4ff08c555b31bd348c9025929371763b2183172ff4708152f0 \
+    --hash=sha256:587f3e19696f4bf96fde9d8a57cec74a57021ad5f204c9e627e15c33ff568897 \
+    --hash=sha256:5d8c8015b24a7d6855b1550d8e660d8daa09983c80e5daf89a273e5c6fb5095a \
+    --hash=sha256:71b3322d949b4cc20776436a9c9ba0eeedcbc9c650daa536df63f0ff111bb920 \
+    --hash=sha256:7873ca4dc60ab3287919881a7d4f88baee4a6e639aa6962de25a98ba6b193341 \
+    --hash=sha256:796ff4426437896550d2981b9c2ac0ffd75238ad9ea2d3bfa67a1abd546d262e \
+    --hash=sha256:9b4de86c8d909aed15b7011182c8cab38c8850de36e6afb1f0db22b8959e3091 \
+    --hash=sha256:a5ab5381813b40f264fa3495b98af850098f814a25a63589a8e9eb12560f450c \
+    --hash=sha256:ef313c46d4c18dfb82a2431e3051ac8f112ccee1a34f29c263c583c568db63cd \
+    --hash=sha256:fd380990e792eaf6827fcb7e187b2b4b1cede0585e3d0c9e84201ec27b9905e4
 pyyaml==6.0.2 ; python_version >= "3.10" and python_version < "3.11" \
     --hash=sha256:01179a4a8559ab5de078078f37e5c1a30d76bb88519906844fd7bdea1b7729ff \
     --hash=sha256:0833f8694549e586547b576dcfaba4a6b55b9e96098b36cdc7ebefe667dfed48 \

rvc/infer/infer.py

@@ -1,42 +1,36 @@
+import logging
 import os
-import sys
 import time
-import torch
+from typing import Callable, Coroutine
+
 import librosa
-import logging
-import traceback
+import noisereduce as nr
 import numpy as np
 import soundfile as sf
-import noisereduce as nr
+import torch
 from pedalboard import (
     Pedalboard,
 )
 from pedalboard_native import (
-    Chorus,
-    Distortion,
-    Reverb,
-    PitchShift,
-    Limiter,
-    Gain,
     Bitcrush,
+    Chorus,
     Clipping,
     Compressor,
     Delay,
+    Distortion,
+    Gain,
+    Limiter,
+    PitchShift,
+    Reverb,
 )
 
-now_dir = os.getcwd()
-sys.path.append(now_dir)
-
+from rvc.configs.config import Config
 from rvc.infer.pipeline import Pipeline as VC
-from rvc.lib.utils import load_audio_infer, load_embedding
-from rvc.lib.tools.split_audio import process_audio, merge_audio
 from rvc.lib.algorithm.synthesizers import Synthesizer
-from rvc.configs.config import Config
+from rvc.lib.tools.split_audio import merge_audio, process_audio
+from rvc.lib.utils import load_audio_infer, load_embedding
 
-logging.getLogger("httpx").setLevel(logging.WARNING)
-logging.getLogger("httpcore").setLevel(logging.WARNING)
-logging.getLogger("faiss").setLevel(logging.WARNING)
-logging.getLogger("faiss.loader").setLevel(logging.WARNING)
+log = logging.getLogger(__name__)
 
 
 class VoiceConverter:
@@ -49,9 +43,7 @@ class VoiceConverter:
         Initializes the VoiceConverter with default configuration, and sets up models and parameters.
         """
         self.config = Config()  # Load RVC configuration
-        self.hubert_model = (
-            None  # Initialize the Hubert model (for embedding extraction)
-        )
+        self.hubert_model = None  # Initialize the Hubert model (for embedding extraction)
         self.last_embedder_model = None  # Last used embedder model
         self.tgt_sr = None  # Target sampling rate for the output audio
         self.net_g = None  # Generator network for voice conversion
@@ -71,11 +63,7 @@ class VoiceConverter:
         """
         self.hubert_model = load_embedding(embedder_model, embedder_model_custom)
         self.hubert_model.to(self.config.device)
-        self.hubert_model = (
-            self.hubert_model.half()
-            if self.config.is_half
-            else self.hubert_model.float()
-        )
+        self.hubert_model = self.hubert_model.half() if self.config.is_half else self.hubert_model.float()
         self.hubert_model.eval()
 
     @staticmethod
@@ -89,12 +77,10 @@ class VoiceConverter:
             reduction_strength (float): Strength of the noise reduction. Default is 0.7.
         """
         try:
-            reduced_noise = nr.reduce_noise(
-                y=data, sr=sr, prop_decrease=reduction_strength
-            )
+            reduced_noise = nr.reduce_noise(y=data, sr=sr, prop_decrease=reduction_strength)
             return reduced_noise
         except Exception as error:
-            print(f"An error occurred removing audio noise: {error}")
+            log.error("An error occurred removing audio noise", exc_info=error)
             return None
 
     @staticmethod
@@ -109,7 +95,7 @@ class VoiceConverter:
         """
         try:
             if output_format != "WAV":
-                print(f"Converting audio to {output_format} format...")
+                log.info(f"Converting audio to {output_format} format...")
                 audio, sample_rate = librosa.load(input_path, sr=None)
                 common_sample_rates = [
                     8000,
@@ -123,13 +109,11 @@ class VoiceConverter:
                     48000,
                 ]
                 target_sr = min(common_sample_rates, key=lambda x: abs(x - sample_rate))
-                audio = librosa.resample(
-                    audio, orig_sr=sample_rate, target_sr=target_sr
-                )
+                audio = librosa.resample(audio, orig_sr=sample_rate, target_sr=target_sr)
                 sf.write(output_path, audio, target_sr, format=output_format.lower())
             return output_path
         except Exception as error:
-            print(f"An error occurred converting the audio format: {error}")
+            log.info("An error occurred converting the audio format", exc_info=error)
 
     @staticmethod
     def post_process_audio(
@@ -195,7 +179,7 @@ class VoiceConverter:
             board.append(delay)
         return board(audio_input, sample_rate)
 
-    def convert_audio(
+    async def convert_audio(
         self,
         audio_input_path: str,
         audio_output_path: str,
@@ -221,6 +205,7 @@ class VoiceConverter:
         post_process: bool = False,
         resample_sr: int = 0,
         sid: int = 0,
+        callback: Callable[[float], Coroutine[None, None, None]] | None = None,
         **kwargs,
     ):
         """
@@ -254,9 +239,9 @@ class VoiceConverter:
         self.get_vc(model_path, sid)
         try:
             start_time = time.time()
-            print(f"Converting audio '{audio_input_path}'...")
+            log.info(f"Converting audio '{audio_input_path}'...")
 
-            if upscale_audio == True:
+            if upscale_audio:
                 from audio_upscaler import upscale
 
                 upscale(audio_input_path, audio_input_path)
@@ -274,27 +259,20 @@ class VoiceConverter:
                 self.load_hubert(embedder_model, embedder_model_custom)
                 self.last_embedder_model = embedder_model
 
-            file_index = (
-                index_path.strip()
-                .strip('"')
-                .strip("\n")
-                .strip('"')
-                .strip()
-                .replace("trained", "added")
-            )
+            file_index = index_path.strip().strip('"').strip("\n").strip('"').strip().replace("trained", "added")
 
             if self.tgt_sr != resample_sr >= 16000:
                 self.tgt_sr = resample_sr
 
             if split_audio:
                 chunks, intervals = process_audio(audio, 16000)
-                print(f"Audio split into {len(chunks)} chunks for processing.")
+                log.debug(f"Audio split into {len(chunks)} chunks for processing.")
             else:
                 chunks = []
                 chunks.append(audio)
 
             converted_chunks = []
-            for c in chunks:
+            for ix, c in enumerate(chunks):
                 if self.vc is None:
                     raise Exception("Voice conversion model not loaded.")
                 audio_opt = self.vc.pipeline(
@@ -318,17 +296,14 @@ class VoiceConverter:
                 )
                 converted_chunks.append(audio_opt)
                 if split_audio:
-                    print(f"Converted audio chunk {len(converted_chunks)}")
+                    log.debug(f"Converted audio chunk {len(converted_chunks)}")
+                if callback is not None:
+                    await callback((ix + 1) / len(chunks))
 
-            if split_audio:
-                audio_opt = merge_audio(converted_chunks, intervals, 16000, self.tgt_sr)
-            else:
-                audio_opt = converted_chunks[0]
+            audio_opt = merge_audio(converted_chunks, intervals, 16000, self.tgt_sr) if split_audio else converted_chunks[0]
 
             if clean_audio:
-                cleaned_audio = self.remove_audio_noise(
-                    audio_opt, self.tgt_sr, clean_strength
-                )
+                cleaned_audio = self.remove_audio_noise(audio_opt, self.tgt_sr, clean_strength)
                 if cleaned_audio is not None:
                     audio_opt = cleaned_audio
 
@@ -340,20 +315,13 @@ class VoiceConverter:
                 )
 
             sf.write(audio_output_path, audio_opt, self.tgt_sr, format="WAV")
-            output_path_format = audio_output_path.replace(
-                ".wav", f".{export_format.lower()}"
-            )
-            audio_output_path = self.convert_audio_format(
-                audio_output_path, output_path_format, export_format
-            )
+            output_path_format = audio_output_path.replace(".wav", f".{export_format.lower()}")
+            audio_output_path = self.convert_audio_format(audio_output_path, output_path_format, export_format)
 
             elapsed_time = time.time() - start_time
-            print(
-                f"Conversion completed at '{audio_output_path}' in {elapsed_time:.2f} seconds."
-            )
+            log.info(f"Conversion completed at '{audio_output_path}' in {elapsed_time:.2f} seconds.")
         except Exception as error:
-            print(f"An error occurred during audio conversion: {error}")
-            print(traceback.format_exc())
+            log.error("An error occurred during audio conversion", exc_info=error)
 
     def get_vc(self, weight_root, sid):
         """
@@ -397,11 +365,7 @@ class VoiceConverter:
         Args:
             weight_root (str): Path to the model weights.
         """
-        self.cpt = (
-            torch.load(weight_root, map_location="cpu")
-            if os.path.isfile(weight_root)
-            else None
-        )
+        self.cpt = torch.load(weight_root, map_location="cpu") if os.path.isfile(weight_root) else None
 
     def setup_network(self):
         """
@@ -423,9 +387,7 @@ class VoiceConverter:
             del self.net_g.enc_q
             self.net_g.load_state_dict(self.cpt["weight"], strict=False)
             self.net_g.eval().to(self.config.device)
-            self.net_g = (
-                self.net_g.half() if self.config.is_half else self.net_g.float()
-            )
+            self.net_g = self.net_g.half() if self.config.is_half else self.net_g.float()
 
     def setup_vc_instance(self):
         """

rvc/infer/pipeline.py

@@ -1,24 +1,20 @@
-import os
 import gc
+import logging
+import os
 import re
-import sys
-import torch
-import torch.nn.functional as F
-import torchcrepe
+
 import faiss
 import librosa
 import numpy as np
 import numpy.typing as npt
+import torch
+import torch.nn.functional as F
+import torchcrepe
 from scipy import signal
 from torch import Tensor
 
-now_dir = os.getcwd()
-sys.path.append(now_dir)
-
-from rvc.lib.predictors.RMVPE import RMVPE0Predictor
 from rvc.lib.predictors.FCPE import FCPEF0Predictor
-
-import logging
+from rvc.lib.predictors.RMVPE import RMVPE0Predictor
 
 logging.getLogger("faiss").setLevel(logging.WARNING)
 
@@ -26,9 +22,7 @@ logging.getLogger("faiss").setLevel(logging.WARNING)
 FILTER_ORDER = 5
 CUTOFF_FREQUENCY = 48  # Hz
 SAMPLE_RATE = 16000  # Hz
-bh, ah = signal.butter(
-    N=FILTER_ORDER, Wn=CUTOFF_FREQUENCY, btype="high", fs=SAMPLE_RATE
-)
+bh, ah = signal.butter(N=FILTER_ORDER, Wn=CUTOFF_FREQUENCY, btype="high", fs=SAMPLE_RATE)
 
 input_audio_path2wav: dict[str, npt.NDArray] = {}
 
@@ -82,10 +76,7 @@ class AudioProcessor:
         rms2 = torch.maximum(rms2, torch.zeros_like(rms2) + 1e-6)
 
         # Adjust target audio RMS based on the source audio RMS
-        adjusted_audio = (
-            target_audio
-            * (torch.pow(rms1, 1 - rate) * torch.pow(rms2, rate - 1)).numpy()
-        )
+        adjusted_audio = target_audio * (torch.pow(rms1, 1 - rate) * torch.pow(rms2, rate - 1)).numpy()
         return adjusted_audio
 
 
@@ -317,7 +308,7 @@ class Pipeline:
 
         f0_computation_stack = [fc for fc in f0_computation_stack if fc is not None]
         f0_median_hybrid = None
-        if len(f0_computation_stack) == 1:
+        if len(f0_computation_stack) == 1:  # noqa: SIM108
             f0_median_hybrid = f0_computation_stack[0]
         else:
             f0_median_hybrid = np.nanmedian(f0_computation_stack, axis=0)
@@ -354,9 +345,7 @@ class Pipeline:
         if f0_method == "crepe":
             f0 = self.get_f0_crepe(x, self.f0_min, self.f0_max, p_len, int(hop_length))
         elif f0_method == "crepe-tiny":
-            f0 = self.get_f0_crepe(
-                x, self.f0_min, self.f0_max, p_len, int(hop_length), "tiny"
-            )
+            f0 = self.get_f0_crepe(x, self.f0_min, self.f0_max, p_len, int(hop_length), "tiny")
         elif f0_method == "rmvpe":
             f0 = self.model_rmvpe.infer_from_audio(x, thred=0.03)
         elif f0_method == "fcpe":
@@ -389,21 +378,13 @@ class Pipeline:
         f0 *= pow(2, pitch / 12)
         tf0 = self.sample_rate // self.window
         if inp_f0 is not None:
-            delta_t = np.round(
-                (inp_f0[:, 0].max() - inp_f0[:, 0].min()) * tf0 + 1
-            ).astype("int16")
-            replace_f0 = np.interp(
-                list(range(delta_t)), inp_f0[:, 0] * 100, inp_f0[:, 1]
-            )
+            delta_t = np.round((inp_f0[:, 0].max() - inp_f0[:, 0].min()) * tf0 + 1).astype("int16")
+            replace_f0 = np.interp(list(range(delta_t)), inp_f0[:, 0] * 100, inp_f0[:, 1])
             shape = f0[self.x_pad * tf0 : self.x_pad * tf0 + len(replace_f0)].shape[0]
-            f0[self.x_pad * tf0 : self.x_pad * tf0 + len(replace_f0)] = replace_f0[
-                :shape
-            ]
+            f0[self.x_pad * tf0 : self.x_pad * tf0 + len(replace_f0)] = replace_f0[:shape]
         f0bak = f0.copy()
         f0_mel = 1127 * np.log(1 + f0 / 700)
-        f0_mel[f0_mel > 0] = (f0_mel[f0_mel > 0] - self.f0_mel_min) * 254 / (
-            self.f0_mel_max - self.f0_mel_min
-        ) + 1
+        f0_mel[f0_mel > 0] = (f0_mel[f0_mel > 0] - self.f0_mel_min) * 254 / (self.f0_mel_max - self.f0_mel_min) + 1
         f0_mel[f0_mel <= 1] = 1
         f0_mel[f0_mel > 255] = 255
         f0_coarse = np.rint(f0_mel).astype(np.int32)
@@ -441,58 +422,37 @@ class Pipeline:
             protect: Protection level for preserving the original pitch.
         """
         with torch.no_grad():
-            pitch_guidance = pitch != None and pitchf != None
+            pitch_guidance = pitch is not None and pitchf is not None
             # prepare source audio
-            feats = (
-                torch.from_numpy(audio0).half()
-                if self.is_half
-                else torch.from_numpy(audio0).float()
-            )
+            feats = torch.from_numpy(audio0).half() if self.is_half else torch.from_numpy(audio0).float()
             feats = feats.mean(-1) if feats.dim() == 2 else feats
             assert feats.dim() == 1, feats.dim()
             feats = feats.view(1, -1).to(self.device)
             # extract features
             feats = model(feats)["last_hidden_state"]
-            feats = (
-                model.final_proj(feats[0]).unsqueeze(0) if version == "v1" else feats
-            )
+            feats = model.final_proj(feats[0]).unsqueeze(0) if version == "v1" else feats
             # make a copy for pitch guidance and protection
             feats0 = feats.clone() if pitch_guidance else None
-            if (
-                index
-            ):  # set by parent function, only true if index is available, loaded, and index rate > 0
-                feats = self._retrieve_speaker_embeddings(
-                    feats, index, big_npy, index_rate
-                )
+            if index:  # set by parent function, only true if index is available, loaded, and index rate > 0
+                feats = self._retrieve_speaker_embeddings(feats, index, big_npy, index_rate)
             # feature upsampling
-            feats = F.interpolate(feats.permute(0, 2, 1), scale_factor=2).permute(
-                0, 2, 1
-            )
+            feats = F.interpolate(feats.permute(0, 2, 1), scale_factor=2).permute(0, 2, 1)
             # adjust the length if the audio is short
             p_len = min(audio0.shape[0] // self.window, feats.shape[1])
             if pitch_guidance:
-                feats0 = F.interpolate(feats0.permute(0, 2, 1), scale_factor=2).permute(
-                    0, 2, 1
-                )
+                feats0 = F.interpolate(feats0.permute(0, 2, 1), scale_factor=2).permute(0, 2, 1)
                 pitch, pitchf = pitch[:, :p_len], pitchf[:, :p_len]
                 # Pitch protection blending
                 if protect < 0.5:
                     pitchff = pitchf.clone()
                     pitchff[pitchf > 0] = 1
                     pitchff[pitchf < 1] = protect
-                    feats = feats * pitchff.unsqueeze(-1) + feats0 * (
-                        1 - pitchff.unsqueeze(-1)
-                    )
+                    feats = feats * pitchff.unsqueeze(-1) + feats0 * (1 - pitchff.unsqueeze(-1))
                     feats = feats.to(feats0.dtype)
             else:
                 pitch, pitchf = None, None
             p_len = torch.tensor([p_len], device=self.device).long()
-            audio1 = (
-                (net_g.infer(feats, p_len, pitch, pitchf, sid)[0][0, 0])
-                .data.cpu()
-                .float()
-                .numpy()
-            )
+            audio1 = (net_g.infer(feats, p_len, pitch, pitchf, sid)[0][0, 0]).data.cpu().float().numpy()
             # clean up
             del feats, feats0, p_len
             if torch.cuda.is_available():
@@ -507,10 +467,7 @@ class Pipeline:
         weight /= weight.sum(axis=1, keepdims=True)
         npy = np.sum(big_npy[ix] * np.expand_dims(weight, axis=2), axis=1)
         npy = npy.astype("float16") if self.is_half else npy
-        feats = (
-            torch.from_numpy(npy).unsqueeze(0).to(self.device) * index_rate
-            + (1 - index_rate) * feats
-        )
+        feats = torch.from_numpy(npy).unsqueeze(0).to(self.device) * index_rate + (1 - index_rate) * feats
         return feats
 
     def pipeline(
@@ -590,7 +547,7 @@ class Pipeline:
         inp_f0 = None
         if hasattr(f0_file, "name"):
             try:
-                with open(f0_file.name, "r") as f:
+                with open(f0_file.name) as f:
                     lines = f.read().strip("\n").split("\n")
                 inp_f0 = []
                 for line in lines:
@@ -687,9 +644,7 @@ class Pipeline:
             )
         audio_opt = np.concatenate(audio_opt)
         if volume_envelope != 1:
-            audio_opt = AudioProcessor.change_rms(
-                audio, self.sample_rate, audio_opt, self.sample_rate, volume_envelope
-            )
+            audio_opt = AudioProcessor.change_rms(audio, self.sample_rate, audio_opt, self.sample_rate, volume_envelope)
         # if resample_sr >= self.sample_rate and tgt_sr != resample_sr:
         #    audio_opt = librosa.resample(
         #        audio_opt, orig_sr=tgt_sr, target_sr=resample_sr

rvc/lib/algorithm/commons.py

@@ -1,7 +1,7 @@
-import math
-import torch
 from typing import List, Optional
 
+import torch
+
 
 def init_weights(m, mean=0.0, std=0.01):
     """
@@ -40,9 +40,7 @@ def convert_pad_shape(pad_shape):
     return pad_shape
 
 
-def slice_segments(
-    x: torch.Tensor, ids_str: torch.Tensor, segment_size: int = 4, dim: int = 2
-):
+def slice_segments(x: torch.Tensor, ids_str: torch.Tensor, segment_size: int = 4, dim: int = 2):
     """
     Slice segments from a tensor, handling tensors with different numbers of dimensions.
 
@@ -126,29 +124,3 @@ def sequence_mask(length: torch.Tensor, max_length: Optional[int] = None):
         max_length = length.max()
     x = torch.arange(max_length, dtype=length.dtype, device=length.device)
     return x.unsqueeze(0) < length.unsqueeze(1)
-
-
-def clip_grad_value(parameters, clip_value, norm_type=2):
-    """
-    Clip the gradients of a list of parameters.
-
-    Args:
-        parameters: The list of parameters to clip.
-        clip_value: The maximum value of the gradients.
-        norm_type: The type of norm to use for clipping.
-    """
-    if isinstance(parameters, torch.Tensor):
-        parameters = [parameters]
-    parameters = list(filter(lambda p: p.grad is not None, parameters))
-    norm_type = float(norm_type)
-    if clip_value is not None:
-        clip_value = float(clip_value)
-
-    total_norm = 0
-    for p in parameters:
-        param_norm = p.grad.data.norm(norm_type)
-        total_norm += param_norm.item() ** norm_type
-        if clip_value is not None:
-            p.grad.data.clamp_(min=-clip_value, max=clip_value)
-    total_norm = total_norm ** (1.0 / norm_type)
-    return total_norm

rvc/lib/tools/split_audio.py

@@ -1,5 +1,5 @@
-import numpy as np
 import librosa
+import numpy as np
 
 
 def process_audio(audio, sr=16000, silence_thresh=-60, min_silence_len=250):
@@ -18,9 +18,10 @@ def process_audio(audio, sr=16000, silence_thresh=-60, min_silence_len=250):
     """
     frame_length = int(min_silence_len / 1000 * sr)
     hop_length = frame_length // 2
-    intervals = librosa.effects.split(
-        audio, top_db=-silence_thresh, frame_length=frame_length, hop_length=hop_length
-    )
+    intervals = librosa.effects.split(audio, top_db=-silence_thresh, frame_length=frame_length, hop_length=hop_length)
+    intervals[0, 0] = 0
+    intervals[1:, 0] = intervals[:-1, 1]
+    intervals[-1, 1] = len(audio)
     audio_segments = [audio[start:end] for start, end in intervals]
 
     return audio_segments, intervals

tabs/tts/tts.py

@@ -1,11 +1,15 @@
+from pathlib import Path
+
 import gradio as gr
 
 from assets.i18n.i18n import I18nAuto
-from core import run_tts_script
+from tts_service.tts import run_tts_script
 from tts_service.voices import voice_manager
 
 i18n = I18nAuto()
 
+sample = Path("notebooks/sample.txt").read_text()
+
 
 # TTS tab
 def tts_tab():
@@ -32,6 +36,7 @@ def tts_tab():
         label=i18n("Text to Synthesize"),
         info=i18n("Enter the text to synthesize."),
         placeholder=i18n("Enter text to synthesize"),
+        value=sample,
         lines=3,
     )
 

tabs/workflow/workflow.py

@@ -0,0 +1,72 @@
+import gradio as gr
+
+from assets.i18n.i18n import I18nAuto
+from tts_service.docs import document_manager
+from tts_service.tts import run_tts_script
+from tts_service.utils import html_to_markdown, markdown_to_text
+
+i18n = I18nAuto()
+
+
+async def fetch_document(source: str) -> tuple[str, gr.Dataset]:
+    doc = await document_manager.get_doc(source)
+    if doc:
+        overline = doc.get("overline")
+        title = doc.get("title")
+        underline = doc.get("underline")
+        authors = doc.get("authors")
+        content = doc["content"]
+        pieces = []
+        if overline:
+            pieces.append(f"### {overline}")
+        if title:
+            pieces.append(f"# {title}")
+        if underline:
+            pieces.append(f"### {underline}")
+        if authors:
+            pieces.append(f"#### By {','.join(authors)}")
+        content = html_to_markdown(content)
+        pieces.append(content)
+        content = "\n\n".join(pieces)
+        text = markdown_to_text(content)
+        return content, text
+    return "", ""
+
+
+# TTS tab
+def workflow_tab():
+    with gr.Row():
+        with gr.Column():
+            source = gr.Textbox(
+                label=i18n("Source"),
+                info=i18n("Enter the document ID or URL."),
+            )
+            fetch_button = gr.Button(i18n("Fetch"))
+
+            text = gr.Textbox(
+                label=i18n("Text"),
+                interactive=True,
+            )
+
+            synthesize_button = gr.Button(i18n("Synthesize"))
+
+            status = gr.Textbox(visible=False)
+
+            audio = gr.Audio(label=i18n("Export Audio"))
+
+        with gr.Column():
+            markdown = gr.Markdown(
+                label=i18n("Document"),
+            )
+
+    fetch_button.click(
+        fn=fetch_document,
+        inputs=[source],
+        outputs=[markdown, text],
+    )
+
+    synthesize_button.click(
+        fn=run_tts_script,
+        inputs=[text],
+        outputs=[status, audio],
+    )

tts_service/app.py

@@ -1,14 +1,16 @@
 import logging
 import sys
+from pathlib import Path
 
 import gradio as gr
+import yaml
 
 import assets.installation_checker as installation_checker
 import assets.themes.loadThemes as loadThemes
 from assets.i18n.i18n import I18nAuto
-from core import run_prerequisites_script
+from rvc.lib.tools.prerequisites_download import prequisites_download_pipeline
 from tabs.plugins import plugins_core
-from tabs.tts.tts import tts_tab
+from tabs.workflow.workflow import workflow_tab
 from tts_service.utils import env_bool
 
 # Set up logging
@@ -20,8 +22,7 @@ logging.getLogger("httpx").setLevel(logging.WARNING)
 plugins_core.check_new_folders()
 
 # Run prerequisites
-
-run_prerequisites_script(
+prequisites_download_pipeline(
     pretraineds_v1_f0=False,
     pretraineds_v1_nof0=False,
     pretraineds_v2_f0=True,
@@ -45,12 +46,23 @@ my_applio = loadThemes.load_theme() or "ParityError/Interstellar"
 # Define Gradio interface
 with gr.Blocks(theme=my_applio, title="TTS Playground", css="footer{display:none !important}") as app:
     gr.Markdown("# Text-to-Speech Playground")
-    gr.Markdown(i18n("Select a voice model, enter text, and press 'Convert' to synthesize speech."))
-    with gr.Tab(i18n("TTS")):
-        tts_tab()
+    gr.Markdown(i18n("Enter a page URL, click fetch and then synthesize"))
+    with gr.Tab(i18n("Workflow")):
+        workflow_tab()
+
+
+def setup_logging():
+    path = Path("logging.yml")
+    if not path.exists():
+        return
+    with path.open() as f:
+        from logging.config import dictConfig
+
+        dictConfig(yaml.safe_load(f))
 
 
 def launch_gradio():
+    setup_logging()
     app.queue(status_update_rate=1).launch(
         favicon_path="assets/ICON.ico",
         share="--share" in sys.argv,

tts_service/docs.py

@@ -0,0 +1,151 @@
+import json
+import logging
+import re
+from typing import Any, TypedDict
+
+import httpx
+
+from tts_service.utils import env_str
+
+
+class WorkflowData(TypedDict):
+    status: str
+    writers: list[str]
+    editors: list[str]
+    proofers: list[str]
+    reviewers: list[str]
+    proofingDeadline: str
+
+
+class Document(TypedDict):
+    _id: str
+    _rev: str
+    type: str
+    mimetype: str
+    title: str
+    language: str
+    workflowData: WorkflowData
+    path: str
+    name: str
+    created: int
+    creator: str
+    lastPublished: int
+    firstPublished: int
+    modified: int
+    modifier: str
+    published: int
+    authors: list[str]
+    content: str
+    contentAssets: list[str]
+    featuredImages: list[str]
+    keywords: list[str]
+    topics: list[str]
+    relatedAssets: list[str]
+    comments: bool
+    campaignConfigs: list[Any]
+    order: int
+    overline: str
+    translatedFrom: str
+    socialTitles: list[Any]
+    socialDescriptions: list[Any]
+    socialFeaturedImages: list[Any]
+    underline: str
+    template: str
+    description: str
+    suggestedImages: list[str]
+    publisher: str
+
+
+class DocumentManager:
+    def __init__(self) -> None:
+        self.client = self.make_client()
+        self.path_view = env_str("DOCS_PATH_VIEW")
+
+    def make_client(self) -> httpx.AsyncClient:
+        base_url = env_str("DOCS_URL")
+        auth = env_str("DOCS_AUTH")
+        headers = {"Authorization": f"Basic {auth}"}
+        client = httpx.AsyncClient(base_url=base_url, headers=headers)
+        return client
+
+    async def get_doc_by_id(self, doc_id: str) -> Document | None:
+        try:
+            response = await self.client.get(doc_id)
+            if response.status_code == 404:
+                return None
+            response.raise_for_status()
+            return response.json()
+        except Exception as e:
+            logging.error("Error fetching document by ID", exc_info=e)
+            return None
+
+    async def get_doc_by_path(self, path: str) -> Document | None:
+        try:
+            params = {
+                "limit": "1",
+                "key": json.dumps(path),
+                "include_docs": "true",
+            }
+            response = await self.client.get(self.path_view, params=params)
+            response.raise_for_status()
+            data = response.json()
+            rows = data["rows"]
+            if not rows:
+                return None
+            return rows[0]["doc"]
+        except Exception as e:
+            logging.error("Error fetching document by path", exc_info=e)
+            return None
+
+    async def get_doc(self, id_or_path: str) -> Document | None:
+        uuids = extract_doc_ids(id_or_path)
+        for uuid in uuids:
+            doc = await self.get_doc_by_id(uuid)
+            if doc:
+                return doc
+
+        path = extract_doc_path(id_or_path)
+        if path:
+            return await self.get_doc_by_path(path)
+
+        return None
+
+
+UUID_PATTERN = re.compile(r"[0-9a-f]{8}-[0-9a-f]{4}-[1-5][0-9a-f]{3}-[89ab][0-9a-f]{3}-[0-9a-f]{12}")
+
+
+def extract_doc_ids(s: str) -> list[str]:
+    return UUID_PATTERN.findall(s)
+
+
+def extract_doc_path(s: str) -> str | None:
+    if not s.endswith(".html"):
+        return None
+    if s.startswith("/"):
+        return s
+    if "://" in s:
+        s = s.split("://", 1)[1]
+        if "/" in s:
+            return "/" + s.split("/", 1)[1]
+    return None
+
+
+document_manager = DocumentManager()
+
+
+if __name__ == "__main__":
+
+    async def main() -> None:
+        db = DocumentManager()
+        # result = await db.get_doc_by_id("b7fdc644-5b24-40ae-b489-37b3fc0c5541")
+        # result = await db.get_doc_by_path("/en/articles/2024/11/28/slci-n28.html")
+        # result = await db.get_doc("https://www.cnn.com/en/articles/2024/11/28/slci-n28.html")
+        result = await db.get_doc("https://bbc.com/news/the-2024-us-elections-efb37bf1-16bb-4bbb-88ce-4273cf657c11")
+        print(json.dumps(result, indent=2))
+
+    import asyncio
+
+    from dotenv import load_dotenv
+
+    load_dotenv()
+    asyncio.run(main())

tts_service/tts.py

@@ -0,0 +1,110 @@
+import asyncio
+import json
+import logging
+import os
+from functools import lru_cache
+
+import edge_tts
+import gradio as gr
+
+from tts_service.utils import cache_path
+from tts_service.voices import voice_manager
+
+log = logging.getLogger(__name__)
+
+
+@lru_cache(maxsize=None)
+def import_voice_converter():
+    from rvc.infer.infer import VoiceConverter
+
+    return VoiceConverter()
+
+
+# TTS
+async def run_tts_script(
+    text: str,
+    voice_name: str = "male-1",
+    rate: int = 0,
+    progress=gr.Progress(),  # noqa: B008
+) -> tuple[str, str]:
+    async def update_progress(pct, msg) -> None:
+        log.debug("Progress: %.1f%%: %s", pct * 100, msg)
+        progress(pct, msg)
+        await asyncio.sleep(0)
+
+    await update_progress(0, "Starting...")
+    voice = voice_manager.voices[voice_name]
+    format = "wav"
+
+    text = text.strip()
+    output_tts_path = cache_path(voice.tts, "", rate, text, extension=format)
+    text_ptr = 0
+    if not os.path.exists(output_tts_path):
+        rates = f"+{rate}%" if rate >= 0 else f"{rate}%"
+        communicate = edge_tts.Communicate(text, voice.tts, rate=rates)
+        with open(output_tts_path, "wb") as f:
+            async for chunk in communicate.stream():
+                chunk_type = chunk["type"]
+                if chunk_type == "audio":
+                    f.write(chunk["data"])
+                elif chunk_type == "WordBoundary":
+                    chunk_text = chunk["text"]
+                    text_index = text.index(chunk_text, text_ptr)
+                    if text_index == -1:
+                        log.warning("Extraneous text received from edge tts: %s", chunk_text)
+                        continue
+                    text_ptr = text_index + len(chunk_text)
+                    pct_complete = text_ptr / len(text)
+                    log.debug("%.1f%%: %s", pct_complete * 100, chunk)
+                    await update_progress(pct_complete / 2, "Synthesizing...")
+                else:
+                    log.warning("Unknown chunk type: %s: %s", chunk_type, json.dumps(chunk))
+
+    output_rvc_path = cache_path(voice.tts, voice.name, rate, text, extension=format)
+    if not os.path.exists(output_rvc_path):
+        infer_pipeline = import_voice_converter()
+        await infer_pipeline.convert_audio(
+            pitch=voice.pitch,
+            filter_radius=voice.filter_radius,
+            index_rate=voice.index_rate,
+            volume_envelope=voice.rms_mix_rate,
+            protect=voice.protect,
+            hop_length=voice.hop_length,
+            f0_method=voice.f0_method,
+            audio_input_path=str(output_tts_path),
+            audio_output_path=str(output_rvc_path),
+            model_path=voice.model,
+            index_path=voice.index,
+            split_audio=True,
+            f0_autotune=voice.autotune is not None,
+            f0_autotune_strength=voice.autotune,
+            clean_audio=voice.clean is not None,
+            clean_strength=voice.clean,
+            export_format=format.upper(),
+            upscale_audio=voice.upscale,
+            f0_file=None,
+            embedder_model=voice.embedder_model,
+            embedder_model_custom=None,
+            sid=0,
+            formant_shifting=None,
+            formant_qfrency=None,
+            formant_timbre=None,
+            post_process=None,
+            reverb=None,
+            pitch_shift=None,
+            limiter=None,
+            gain=None,
+            distortion=None,
+            chorus=None,
+            bitcrush=None,
+            clipping=None,
+            compressor=None,
+            delay=None,
+            sliders=None,
+            callback=lambda pct: update_progress(0.5 + pct / 2, "Converting..."),
+        )
+
+    return "Text synthesized successfully.", str(output_rvc_path)
+
+
+# Prerequisites

tts_service/utils.py

@@ -1,7 +1,9 @@
 import hashlib
 import os
 from pathlib import Path
-from typing import Any
+from typing import Any, cast
+
+import pandoc
 
 
 class Unspecified:
@@ -47,3 +49,15 @@ def cache_path(*keys: Any, extension: str | None = None) -> Path:
     if extension:
         name += f".{extension}"
     return dir_path / name
+
+
+def html_to_markdown(html: str) -> str:
+    doc = pandoc.read(html, format="html")
+    md = pandoc.write(doc, format="markdown-smart", options=["--wrap=none"])
+    return cast(str, md)
+
+
+def markdown_to_text(md: str) -> str:
+    doc = pandoc.read(md, format="markdown")
+    txt = pandoc.write(doc, format="plain-smart", options=["--wrap=none"])
+    return cast(str, txt)

tts_service/whitelist.py

@@ -11,12 +11,33 @@ _.secondary_800  # unused attribute (assets/themes/Applio.py:52)
 _.secondary_900  # unused attribute (assets/themes/Applio.py:53)
 _.secondary_950  # unused attribute (assets/themes/Applio.py:54)
 __getattr__  # unused function (rvc/lib/predictors/FCPE.py:799)
-_.graph  # unused attribute (rvc/lib/zluda.py:33)
-_.enabled  # unused attribute (rvc/lib/zluda.py:40)
-_.nprobe  # unused attribute (rvc/train/process/extract_index.py:76)
-rvc  # unused import (rvc/train/train.py:28)
-_.deterministic  # unused attribute (rvc/train/train.py:78)
-_.benchmark  # unused attribute (rvc/train/train.py:79)
-losses_disc_g  # unused variable (rvc/train/train.py:630)
-losses_disc_r  # unused variable (rvc/train/train.py:630)
-losses_gen  # unused variable (rvc/train/train.py:649)
+status  # unused variable (tts_service/docs.py:12)
+writers  # unused variable (tts_service/docs.py:13)
+editors  # unused variable (tts_service/docs.py:14)
+proofers  # unused variable (tts_service/docs.py:15)
+reviewers  # unused variable (tts_service/docs.py:16)
+proofingDeadline  # unused variable (tts_service/docs.py:17)
+mimetype  # unused variable (tts_service/docs.py:24)
+workflowData  # unused variable (tts_service/docs.py:27)
+created  # unused variable (tts_service/docs.py:30)
+creator  # unused variable (tts_service/docs.py:31)
+lastPublished  # unused variable (tts_service/docs.py:32)
+firstPublished  # unused variable (tts_service/docs.py:33)
+modified  # unused variable (tts_service/docs.py:34)
+modifier  # unused variable (tts_service/docs.py:35)
+published  # unused variable (tts_service/docs.py:36)
+contentAssets  # unused variable (tts_service/docs.py:39)
+featuredImages  # unused variable (tts_service/docs.py:40)
+keywords  # unused variable (tts_service/docs.py:41)
+topics  # unused variable (tts_service/docs.py:42)
+relatedAssets  # unused variable (tts_service/docs.py:43)
+comments  # unused variable (tts_service/docs.py:44)
+campaignConfigs  # unused variable (tts_service/docs.py:45)
+order  # unused variable (tts_service/docs.py:46)
+translatedFrom  # unused variable (tts_service/docs.py:48)
+socialTitles  # unused variable (tts_service/docs.py:49)
+socialDescriptions  # unused variable (tts_service/docs.py:50)
+socialFeaturedImages  # unused variable (tts_service/docs.py:51)
+description  # unused variable (tts_service/docs.py:54)
+suggestedImages  # unused variable (tts_service/docs.py:55)
+publisher  # unused variable (tts_service/docs.py:56)