build: adicionado parametros
Browse files- .gitignore +178 -0
- __pycache__/app.cpython-310.pyc +0 -0
- __pycache__/utils.cpython-310.pyc +0 -0
- app.py +24 -22
- requirements.txt +2 -1
- utils.py +39 -23
.gitignore
ADDED
@@ -0,0 +1,178 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Created by https://www.toptal.com/developers/gitignore/api/python
|
2 |
+
# Edit at https://www.toptal.com/developers/gitignore?templates=python
|
3 |
+
|
4 |
+
### Python ###
|
5 |
+
# Byte-compiled / optimized / DLL files
|
6 |
+
__pycache__/
|
7 |
+
*.py[cod]
|
8 |
+
*$py.class
|
9 |
+
|
10 |
+
# C extensions
|
11 |
+
*.so
|
12 |
+
|
13 |
+
# Distribution / packaging
|
14 |
+
.Python
|
15 |
+
build/
|
16 |
+
develop-eggs/
|
17 |
+
dist/
|
18 |
+
downloads/
|
19 |
+
eggs/
|
20 |
+
.eggs/
|
21 |
+
lib/
|
22 |
+
lib64/
|
23 |
+
parts/
|
24 |
+
sdist/
|
25 |
+
var/
|
26 |
+
wheels/
|
27 |
+
share/python-wheels/
|
28 |
+
*.egg-info/
|
29 |
+
.installed.cfg
|
30 |
+
*.egg
|
31 |
+
MANIFEST
|
32 |
+
|
33 |
+
# PyInstaller
|
34 |
+
# Usually these files are written by a python script from a template
|
35 |
+
# before PyInstaller builds the exe, so as to inject date/other infos into it.
|
36 |
+
*.manifest
|
37 |
+
*.spec
|
38 |
+
|
39 |
+
# Installer logs
|
40 |
+
pip-log.txt
|
41 |
+
pip-delete-this-directory.txt
|
42 |
+
|
43 |
+
# Unit test / coverage reports
|
44 |
+
htmlcov/
|
45 |
+
.tox/
|
46 |
+
.nox/
|
47 |
+
.coverage
|
48 |
+
.coverage.*
|
49 |
+
.cache
|
50 |
+
nosetests.xml
|
51 |
+
coverage.xml
|
52 |
+
*.cover
|
53 |
+
*.py,cover
|
54 |
+
.hypothesis/
|
55 |
+
.pytest_cache/
|
56 |
+
cover/
|
57 |
+
|
58 |
+
# Translations
|
59 |
+
*.mo
|
60 |
+
*.pot
|
61 |
+
|
62 |
+
# Django stuff:
|
63 |
+
*.log
|
64 |
+
local_settings.py
|
65 |
+
db.sqlite3
|
66 |
+
db.sqlite3-journal
|
67 |
+
|
68 |
+
# Flask stuff:
|
69 |
+
instance/
|
70 |
+
.webassets-cache
|
71 |
+
|
72 |
+
# Scrapy stuff:
|
73 |
+
.scrapy
|
74 |
+
|
75 |
+
# Sphinx documentation
|
76 |
+
docs/_build/
|
77 |
+
|
78 |
+
# PyBuilder
|
79 |
+
.pybuilder/
|
80 |
+
target/
|
81 |
+
|
82 |
+
# Jupyter Notebook
|
83 |
+
.ipynb_checkpoints
|
84 |
+
|
85 |
+
# IPython
|
86 |
+
profile_default/
|
87 |
+
ipython_config.py
|
88 |
+
|
89 |
+
# pyenv
|
90 |
+
# For a library or package, you might want to ignore these files since the code is
|
91 |
+
# intended to run in multiple environments; otherwise, check them in:
|
92 |
+
# .python-version
|
93 |
+
|
94 |
+
# pipenv
|
95 |
+
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
|
96 |
+
# However, in case of collaboration, if having platform-specific dependencies or dependencies
|
97 |
+
# having no cross-platform support, pipenv may install dependencies that don't work, or not
|
98 |
+
# install all needed dependencies.
|
99 |
+
#Pipfile.lock
|
100 |
+
|
101 |
+
# poetry
|
102 |
+
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
|
103 |
+
# This is especially recommended for binary packages to ensure reproducibility, and is more
|
104 |
+
# commonly ignored for libraries.
|
105 |
+
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
|
106 |
+
#poetry.lock
|
107 |
+
|
108 |
+
# pdm
|
109 |
+
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
|
110 |
+
#pdm.lock
|
111 |
+
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
|
112 |
+
# in version control.
|
113 |
+
# https://pdm.fming.dev/#use-with-ide
|
114 |
+
.pdm.toml
|
115 |
+
|
116 |
+
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
|
117 |
+
__pypackages__/
|
118 |
+
|
119 |
+
# Celery stuff
|
120 |
+
celerybeat-schedule
|
121 |
+
celerybeat.pid
|
122 |
+
|
123 |
+
# SageMath parsed files
|
124 |
+
*.sage.py
|
125 |
+
|
126 |
+
# Environments
|
127 |
+
.env
|
128 |
+
.venv
|
129 |
+
env/
|
130 |
+
venv/
|
131 |
+
ENV/
|
132 |
+
env.bak/
|
133 |
+
venv.bak/
|
134 |
+
|
135 |
+
# Spyder project settings
|
136 |
+
.spyderproject
|
137 |
+
.spyproject
|
138 |
+
|
139 |
+
# Rope project settings
|
140 |
+
.ropeproject
|
141 |
+
|
142 |
+
# mkdocs documentation
|
143 |
+
/site
|
144 |
+
|
145 |
+
# mypy
|
146 |
+
.mypy_cache/
|
147 |
+
.dmypy.json
|
148 |
+
dmypy.json
|
149 |
+
|
150 |
+
# Pyre type checker
|
151 |
+
.pyre/
|
152 |
+
|
153 |
+
# pytype static type analyzer
|
154 |
+
.pytype/
|
155 |
+
|
156 |
+
# Cython debug symbols
|
157 |
+
cython_debug/
|
158 |
+
|
159 |
+
# PyCharm
|
160 |
+
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
|
161 |
+
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
|
162 |
+
# and can be added to the global gitignore or merged into this file. For a more nuclear
|
163 |
+
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
|
164 |
+
#.idea/
|
165 |
+
|
166 |
+
### Python Patch ###
|
167 |
+
# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
|
168 |
+
poetry.toml
|
169 |
+
|
170 |
+
# ruff
|
171 |
+
.ruff_cache/
|
172 |
+
|
173 |
+
# LSP config files
|
174 |
+
pyrightconfig.json
|
175 |
+
|
176 |
+
# End of https://www.toptal.com/developers/gitignore/api/python
|
177 |
+
|
178 |
+
.voice
|
__pycache__/app.cpython-310.pyc
DELETED
Binary file (1.91 kB)
|
|
__pycache__/utils.cpython-310.pyc
DELETED
Binary file (5.62 kB)
|
|
app.py
CHANGED
@@ -1,17 +1,25 @@
|
|
1 |
"""Deploying AI Voice Chatbot Gradio App."""
|
2 |
from gradio import Audio, Interface, Textbox, Checkbox
|
3 |
from typing import Tuple
|
4 |
-
|
|
|
5 |
from utils import (TextGenerationPipeline, from_en_translation,
|
6 |
html_audio_autoplay, stt, to_en_translation, tts,
|
7 |
tts_polly, tts_to_bytesio, tts_polly_to_bytesio)
|
8 |
|
9 |
-
|
10 |
-
|
|
|
|
|
|
|
|
|
11 |
response_generator_pipe = TextGenerationPipeline(max_length=max_answer_length)
|
12 |
|
13 |
|
14 |
-
def main(audio: object, use_polly: bool) -> Tuple[str, str,
|
|
|
|
|
|
|
15 |
"""Calls functions for deploying gradio app.
|
16 |
|
17 |
It responds both verbally and in text
|
@@ -24,44 +32,38 @@ def main(audio: object, use_polly: bool) -> Tuple[str, str, str, object]:
|
|
24 |
tuple containing
|
25 |
|
26 |
- user_speech_text (str) : recognized speech
|
27 |
-
-
|
28 |
- bot_response_en (str) : bot's original answer
|
29 |
- html (object) : autoplayer for bot's speech
|
30 |
"""
|
31 |
user_speech_text = stt(audio, desired_language)
|
32 |
-
|
33 |
-
bot_response_en = response_generator_pipe(
|
34 |
-
|
|
|
35 |
if use_polly:
|
36 |
-
bot_voice = tts_polly(
|
37 |
bot_voice_bytes = tts_polly_to_bytesio(bot_voice)
|
38 |
else:
|
39 |
-
bot_voice = tts(
|
40 |
bot_voice_bytes = tts_to_bytesio(bot_voice)
|
41 |
-
|
42 |
html = html_audio_autoplay(bot_voice_bytes)
|
43 |
-
return user_speech_text,
|
44 |
|
45 |
|
46 |
demo = Interface(
|
47 |
fn=main,
|
48 |
inputs=[
|
49 |
-
Audio(
|
50 |
-
|
51 |
-
type="filepath",
|
52 |
-
),
|
53 |
-
Checkbox(
|
54 |
-
value=False,
|
55 |
-
label="Usar Polly?"
|
56 |
-
)
|
57 |
],
|
58 |
outputs=[
|
59 |
Textbox(label="Você disse: "),
|
60 |
Textbox(label="AI disse: "),
|
61 |
-
Textbox(label="AI disse (English): "),
|
62 |
"html",
|
63 |
],
|
64 |
live=True,
|
65 |
allow_flagging="never")
|
66 |
|
67 |
-
demo.launch(debug=
|
|
|
1 |
"""Deploying AI Voice Chatbot Gradio App."""
|
2 |
from gradio import Audio, Interface, Textbox, Checkbox
|
3 |
from typing import Tuple
|
4 |
+
from dotenv import load_dotenv
|
5 |
+
import os
|
6 |
from utils import (TextGenerationPipeline, from_en_translation,
|
7 |
html_audio_autoplay, stt, to_en_translation, tts,
|
8 |
tts_polly, tts_to_bytesio, tts_polly_to_bytesio)
|
9 |
|
10 |
+
load_dotenv()
|
11 |
+
|
12 |
+
max_answer_length = os.getenv('MAX_ANSWER_LENGTH', 100)
|
13 |
+
desired_language = os.getenv('DESIRED_LANGUAGE', 'pt')
|
14 |
+
polly_language = os.getenv('POLLY_LANGUAGE_LANGUAGE', 'pt-BR')
|
15 |
+
|
16 |
response_generator_pipe = TextGenerationPipeline(max_length=max_answer_length)
|
17 |
|
18 |
|
19 |
+
def main(audio: object, use_polly: bool) -> Tuple[str, str, object]:
|
20 |
+
if audio is None:
|
21 |
+
return "", "", ""
|
22 |
+
|
23 |
"""Calls functions for deploying gradio app.
|
24 |
|
25 |
It responds both verbally and in text
|
|
|
32 |
tuple containing
|
33 |
|
34 |
- user_speech_text (str) : recognized speech
|
35 |
+
- bot_response_pt (str) : translated answer of bot
|
36 |
- bot_response_en (str) : bot's original answer
|
37 |
- html (object) : autoplayer for bot's speech
|
38 |
"""
|
39 |
user_speech_text = stt(audio, desired_language)
|
40 |
+
translated_text = to_en_translation(user_speech_text, desired_language)
|
41 |
+
bot_response_en = response_generator_pipe(translated_text)
|
42 |
+
bot_response_pt = from_en_translation(bot_response_en, desired_language)
|
43 |
+
|
44 |
if use_polly:
|
45 |
+
bot_voice = tts_polly(bot_response_pt, polly_language)
|
46 |
bot_voice_bytes = tts_polly_to_bytesio(bot_voice)
|
47 |
else:
|
48 |
+
bot_voice = tts(bot_response_pt, desired_language)
|
49 |
bot_voice_bytes = tts_to_bytesio(bot_voice)
|
50 |
+
|
51 |
html = html_audio_autoplay(bot_voice_bytes)
|
52 |
+
return user_speech_text, bot_response_pt, html
|
53 |
|
54 |
|
55 |
demo = Interface(
|
56 |
fn=main,
|
57 |
inputs=[
|
58 |
+
Audio(source="microphone", type="filepath"),
|
59 |
+
Checkbox(value=False, label="Usar Polly?")
|
|
|
|
|
|
|
|
|
|
|
|
|
60 |
],
|
61 |
outputs=[
|
62 |
Textbox(label="Você disse: "),
|
63 |
Textbox(label="AI disse: "),
|
|
|
64 |
"html",
|
65 |
],
|
66 |
live=True,
|
67 |
allow_flagging="never")
|
68 |
|
69 |
+
demo.launch(debug=False)
|
requirements.txt
CHANGED
@@ -5,4 +5,5 @@ SpeechRecognition==3.9.0
|
|
5 |
mtranslate==1.8
|
6 |
gTTS==2.3.0
|
7 |
transformers==4.25.1
|
8 |
-
boto3
|
|
|
|
5 |
mtranslate==1.8
|
6 |
gTTS==2.3.0
|
7 |
transformers==4.25.1
|
8 |
+
boto3
|
9 |
+
python-dotenv
|
utils.py
CHANGED
@@ -1,11 +1,8 @@
|
|
1 |
"""Some utility functions for the app."""
|
2 |
from base64 import b64encode
|
3 |
from io import BytesIO
|
4 |
-
|
5 |
import os
|
6 |
import sys
|
7 |
-
from tempfile import gettempdir
|
8 |
-
|
9 |
from gtts import gTTS
|
10 |
from mtranslate import translate
|
11 |
from speech_recognition import AudioFile, Recognizer
|
@@ -13,10 +10,21 @@ from transformers import (BlenderbotSmallForConditionalGeneration,
|
|
13 |
BlenderbotSmallTokenizer)
|
14 |
from contextlib import closing
|
15 |
import boto3
|
|
|
16 |
|
17 |
-
|
18 |
|
19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
def stt(audio: object, language: str) -> str:
|
21 |
"""Converts speech to text.
|
22 |
|
@@ -132,16 +140,27 @@ def tts(text: str, language: str) -> object:
|
|
132 |
return gTTS(text=text, lang=language, slow=False)
|
133 |
|
134 |
|
135 |
-
def tts_polly(text: str) -> object:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
136 |
response = client.synthesize_speech(
|
137 |
Engine='neural',
|
138 |
-
LanguageCode='pt-BR',
|
139 |
OutputFormat='mp3',
|
140 |
-
|
141 |
-
|
142 |
-
|
|
|
143 |
return response
|
144 |
|
|
|
145 |
def tts_polly_to_bytesio(polly_object: object) -> bytes:
|
146 |
# Access the audio stream from the response
|
147 |
if "AudioStream" in polly_object:
|
@@ -149,26 +168,23 @@ def tts_polly_to_bytesio(polly_object: object) -> bytes:
|
|
149 |
# number of parallel connections. Here we are using contextlib.closing to
|
150 |
# ensure the close method of the stream object will be called automatically
|
151 |
# at the end of the with statement's scope.
|
152 |
-
|
153 |
-
|
154 |
-
|
155 |
-
|
156 |
-
|
157 |
-
|
158 |
-
|
159 |
-
|
160 |
-
|
161 |
-
|
162 |
-
except IOError as error:
|
163 |
-
# Could not write to file, exit gracefully
|
164 |
-
print(error)
|
165 |
-
sys.exit(-1)
|
166 |
|
167 |
else:
|
168 |
# The response didn't contain audio data, exit gracefully
|
169 |
print("Could not stream audio")
|
170 |
sys.exit(-1)
|
171 |
|
|
|
172 |
def tts_to_bytesio(tts_object: object) -> bytes:
|
173 |
"""Converts tts object to bytes.
|
174 |
|
|
|
1 |
"""Some utility functions for the app."""
|
2 |
from base64 import b64encode
|
3 |
from io import BytesIO
|
|
|
4 |
import os
|
5 |
import sys
|
|
|
|
|
6 |
from gtts import gTTS
|
7 |
from mtranslate import translate
|
8 |
from speech_recognition import AudioFile, Recognizer
|
|
|
10 |
BlenderbotSmallTokenizer)
|
11 |
from contextlib import closing
|
12 |
import boto3
|
13 |
+
from botocore.config import Config
|
14 |
|
15 |
+
import time
|
16 |
|
17 |
|
18 |
+
def log_execution_time(func):
|
19 |
+
def wrapper(*args, **kwargs):
|
20 |
+
start_time = time.time()
|
21 |
+
result = func(*args, **kwargs)
|
22 |
+
end_time = time.time()
|
23 |
+
execution_time = end_time - start_time
|
24 |
+
print(f"Execution time of {func.__name__}: {execution_time} seconds")
|
25 |
+
return result
|
26 |
+
return wrapper
|
27 |
+
|
28 |
def stt(audio: object, language: str) -> str:
|
29 |
"""Converts speech to text.
|
30 |
|
|
|
140 |
return gTTS(text=text, lang=language, slow=False)
|
141 |
|
142 |
|
143 |
+
def tts_polly(text: str, language: str) -> object:
|
144 |
+
my_config = Config(
|
145 |
+
region_name=os.getenv('AWS_REGION', 'us-east-1'),
|
146 |
+
# signature_version = 'v4',
|
147 |
+
# retries = {
|
148 |
+
# 'max_attempts': 10,
|
149 |
+
# 'mode': 'standard'
|
150 |
+
# }
|
151 |
+
)
|
152 |
+
|
153 |
+
client = boto3.client('polly', config=my_config)
|
154 |
response = client.synthesize_speech(
|
155 |
Engine='neural',
|
|
|
156 |
OutputFormat='mp3',
|
157 |
+
VoiceId='Camila',
|
158 |
+
LanguageCode=language,
|
159 |
+
Text=text)
|
160 |
+
|
161 |
return response
|
162 |
|
163 |
+
|
164 |
def tts_polly_to_bytesio(polly_object: object) -> bytes:
|
165 |
# Access the audio stream from the response
|
166 |
if "AudioStream" in polly_object:
|
|
|
168 |
# number of parallel connections. Here we are using contextlib.closing to
|
169 |
# ensure the close method of the stream object will be called automatically
|
170 |
# at the end of the with statement's scope.
|
171 |
+
with closing(polly_object["AudioStream"]) as stream:
|
172 |
+
try:
|
173 |
+
bytes_object = BytesIO()
|
174 |
+
bytes_object.write(stream.read())
|
175 |
+
bytes_object.seek(0)
|
176 |
+
return bytes_object.getvalue()
|
177 |
+
except IOError as error:
|
178 |
+
# Could not write to bytes, exit gracefully
|
179 |
+
print(error)
|
180 |
+
sys.exit(-1)
|
|
|
|
|
|
|
|
|
181 |
|
182 |
else:
|
183 |
# The response didn't contain audio data, exit gracefully
|
184 |
print("Could not stream audio")
|
185 |
sys.exit(-1)
|
186 |
|
187 |
+
|
188 |
def tts_to_bytesio(tts_object: object) -> bytes:
|
189 |
"""Converts tts object to bytes.
|
190 |
|