build: adicionado parametros

.gitignore

@@ -0,0 +1,178 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+# End of https://www.toptal.com/developers/gitignore/api/python
+
+.voice

app.py

@@ -1,17 +1,25 @@
 """Deploying AI Voice Chatbot Gradio App."""
 from gradio import Audio, Interface, Textbox, Checkbox
 from typing import Tuple
-
+from dotenv import load_dotenv
+import os
 from utils import (TextGenerationPipeline, from_en_translation,
                    html_audio_autoplay, stt, to_en_translation, tts,
                    tts_polly, tts_to_bytesio, tts_polly_to_bytesio)
 
-max_answer_length = 100
-desired_language = "pt"
+load_dotenv()
+
+max_answer_length = os.getenv('MAX_ANSWER_LENGTH', 100)
+desired_language = os.getenv('DESIRED_LANGUAGE', 'pt')
+polly_language = os.getenv('POLLY_LANGUAGE_LANGUAGE', 'pt-BR')
+
 response_generator_pipe = TextGenerationPipeline(max_length=max_answer_length)
 
 
-def main(audio: object, use_polly: bool) -> Tuple[str, str, str, object]:
+def main(audio: object, use_polly: bool) -> Tuple[str, str, object]:
+    if audio is None:
+        return "", "", ""
+
     """Calls functions for deploying gradio app.
 
     It responds both verbally and in text
@@ -24,44 +32,38 @@ def main(audio: object, use_polly: bool) -> Tuple[str, str, str, object]:
         tuple containing
 
         - user_speech_text (str) : recognized speech
-        - bot_response_de (str) : translated answer of bot
+        - bot_response_pt (str) : translated answer of bot
         - bot_response_en (str) : bot's original answer
         - html (object) : autoplayer for bot's speech
     """
     user_speech_text = stt(audio, desired_language)
-    tranlated_text = to_en_translation(user_speech_text, desired_language)
-    bot_response_en = response_generator_pipe(tranlated_text)
-    bot_response_de = from_en_translation(bot_response_en, desired_language)
+    translated_text = to_en_translation(user_speech_text, desired_language)
+    bot_response_en = response_generator_pipe(translated_text)
+    bot_response_pt = from_en_translation(bot_response_en, desired_language)
+
     if use_polly:
-        bot_voice = tts_polly(bot_response_de)
+        bot_voice = tts_polly(bot_response_pt, polly_language)
         bot_voice_bytes = tts_polly_to_bytesio(bot_voice)
     else:
-        bot_voice = tts(bot_response_de, desired_language)
+        bot_voice = tts(bot_response_pt, desired_language)
         bot_voice_bytes = tts_to_bytesio(bot_voice)
-    
+
     html = html_audio_autoplay(bot_voice_bytes)
-    return user_speech_text, bot_response_de, bot_response_en, html
+    return user_speech_text, bot_response_pt, html
 
 
 demo = Interface(
     fn=main,
     inputs=[
-        Audio(
-            source="microphone",
-            type="filepath",
-        ),
-        Checkbox(
-            value=False,
-            label="Usar Polly?"
-        )
+        Audio(source="microphone", type="filepath"),
+        Checkbox(value=False, label="Usar Polly?")
     ],
     outputs=[
         Textbox(label="Você disse: "),
         Textbox(label="AI disse: "),
-        Textbox(label="AI disse (English): "),
         "html",
     ],
     live=True,
     allow_flagging="never")
 
-demo.launch(debug=True)
+demo.launch(debug=False)

requirements.txt

@@ -5,4 +5,5 @@ SpeechRecognition==3.9.0
 mtranslate==1.8
 gTTS==2.3.0
 transformers==4.25.1
-boto3
+boto3
+python-dotenv

utils.py

@@ -1,11 +1,8 @@
 """Some utility functions for the app."""
 from base64 import b64encode
 from io import BytesIO
-
 import os
 import sys
-from tempfile import gettempdir
-
 from gtts import gTTS
 from mtranslate import translate
 from speech_recognition import AudioFile, Recognizer
@@ -13,10 +10,21 @@ from transformers import (BlenderbotSmallForConditionalGeneration,
                           BlenderbotSmallTokenizer)
 from contextlib import closing
 import boto3
+from botocore.config import Config
 
-client = boto3.client('polly')
+import time
 
 
+def log_execution_time(func):
+    def wrapper(*args, **kwargs):
+        start_time = time.time()
+        result = func(*args, **kwargs)
+        end_time = time.time()
+        execution_time = end_time - start_time
+        print(f"Execution time of {func.__name__}: {execution_time} seconds")
+        return result
+    return wrapper
+
 def stt(audio: object, language: str) -> str:
     """Converts speech to text.
 
@@ -132,16 +140,27 @@ def tts(text: str, language: str) -> object:
     return gTTS(text=text, lang=language, slow=False)
 
 
-def tts_polly(text: str) -> object:
+def tts_polly(text: str, language: str) -> object:
+    my_config = Config(
+        region_name=os.getenv('AWS_REGION', 'us-east-1'),
+        # signature_version = 'v4',
+        # retries = {
+        #     'max_attempts': 10,
+        #     'mode': 'standard'
+        # }
+    )
+
+    client = boto3.client('polly', config=my_config)
     response = client.synthesize_speech(
         Engine='neural',
-        LanguageCode='pt-BR',
         OutputFormat='mp3',
-        Text=text,
-        VoiceId='Camila')
-    
+        VoiceId='Camila',
+        LanguageCode=language,
+        Text=text)
+
     return response
 
+
 def tts_polly_to_bytesio(polly_object: object) -> bytes:
     # Access the audio stream from the response
     if "AudioStream" in polly_object:
@@ -149,26 +168,23 @@ def tts_polly_to_bytesio(polly_object: object) -> bytes:
         # number of parallel connections. Here we are using contextlib.closing to
         # ensure the close method of the stream object will be called automatically
         # at the end of the with statement's scope.
-            with closing(polly_object["AudioStream"]) as stream:
-                try:
-                    # output = os.path.join(gettempdir(), "speech.mp3")
-                    bytes_object = BytesIO()
-                    bytes_object.write(stream.read())
-                    # # Open a file for writing the output as a binary stream
-                    # with open(output, "wb") as file:
-                    #     file.write(bytes_object)
-                    bytes_object.seek(0)                    
-                    return bytes_object.getvalue()
-                except IOError as error:
-                    # Could not write to file, exit gracefully
-                    print(error)
-                    sys.exit(-1)
+        with closing(polly_object["AudioStream"]) as stream:
+            try:
+                bytes_object = BytesIO()
+                bytes_object.write(stream.read())
+                bytes_object.seek(0)
+                return bytes_object.getvalue()
+            except IOError as error:
+                # Could not write to bytes, exit gracefully
+                print(error)
+                sys.exit(-1)
 
     else:
         # The response didn't contain audio data, exit gracefully
         print("Could not stream audio")
         sys.exit(-1)
 
+
 def tts_to_bytesio(tts_object: object) -> bytes:
     """Converts tts object to bytes.