First commit

.gitignore

@@ -0,0 +1,134 @@
+# 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/
+pip-wheel-metadata/
+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
+.hypothesis/
+.pytest_cache/
+
+# 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
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__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/

.vscode/settings.json

@@ -0,0 +1,3 @@
+{
+  "python.analysis.extraPaths": ["./src"]
+}

README.md

@@ -0,0 +1,4 @@
+# Sentiment Analysis testing
+
+A simple repo to play with testing for an app to transcribe sentences and get the emotions from them.
+

app.py

@@ -0,0 +1,87 @@
+import gradio as gr
+from src.sentiment import analyze_sentiment
+from src.transcribe import transcribe_audio
+
+TITLE = """<h1 align="center">🎤 Emotion Detection 💬</h1>"""
+
+EMOJI_MAPPING = {
+    "disappointment": "😞",
+    "sadness": "😢",
+    "annoyance": "😠",
+    "neutral": "😐",
+    "disapproval": "👎",
+    "realization": "😮",
+    "nervousness": "😬",
+    "approval": "👍",
+    "joy": "😄",
+    "anger": "😡",
+    "embarrassment": "😳",
+    "caring": "🤗",
+    "remorse": "😔",
+    "disgust": "🤢",
+    "grief": "😥",
+    "confusion": "😕",
+    "relief": "😌",
+    "desire": "😍",
+    "admiration": "😌",
+    "optimism": "😊",
+    "fear": "😨",
+    "love": "❤️",
+    "excitement": "🎉",
+    "curiosity": "🤔",
+    "amusement": "😄",
+    "surprise": "😲",
+    "gratitude": "🙏",
+    "pride": "🦁",
+}
+
+
+def get_sentiment_emoji(sentiment: str) -> str:
+    """Returns the emoji corresponding to the sentiment"""
+    return EMOJI_MAPPING.get(sentiment, "")
+
+
+def display_sentiment_results(sentiment_results: dict) -> str:
+    """Returns the sentiment analysis results as a string"""
+    sentiment_text = ""
+    for sentiment, _ in sentiment_results.items():
+        emoji = get_sentiment_emoji(sentiment)
+        sentiment_text += f"{sentiment} {emoji}\n"
+    return sentiment_text
+
+
+def get_ouput(audio_file: str) -> (str, str):
+    """Returns the transcribed text and the sentiment analysis results"""
+    try:
+        text = transcribe_audio(audio_file)
+        sentiment = analyze_sentiment(text)
+        return text, display_sentiment_results(sentiment)
+    except Exception as e:
+        print(f"Error in transcribe_audio: {e}")
+        return "", "Error in transcription."
+
+
+def main():
+    """Main function"""
+    block = gr.Blocks()
+    with block:
+        gr.HTML(TITLE)
+
+        with gr.Group():
+            audio_input = gr.Audio(sources=["microphone"], type="filepath")
+            output_text = gr.Textbox(label="Transcription")
+            emotion_output = gr.Textbox(label="Emotion Analysis")
+
+            gr.Interface(
+                fn=get_ouput,
+                inputs=audio_input,
+                outputs=[output_text, emotion_output],
+                title="Get the text and the sentiment",
+                description="Upload an audio file and hit the 'Submit'\
+                                  button",
+            )
+    block.launch()
+
+
+if __name__ == "__main__":
+    main()

extra/generate_audio.sh

@@ -0,0 +1,8 @@
+#!/bin/bash
+
+if [[ $(uname) == "Darwin" ]]; then
+    say -v Daniel -f extra/script.txt -o extra/script.aiff
+    lame -m m extra/script.aiff extra/thisisatest.mp3
+else
+    echo "This script only works on Mac OS"
+fi

extra/script.txt

@@ -0,0 +1,4 @@
+[[ slnc 5000 ]]
+[[rate 150]][[volm 0.9]]
+This is a test
+[[ slnc 1300 ]]

pyproject.toml

@@ -0,0 +1,23 @@
+[tool.poetry]
+name = "testing-sentiment"
+version = "0.1.0"
+description = "A simple repo to add testing to a AI app"
+authors = ["Enrique Sanchez <je.sanchezb@gmail.com>"]
+license = "MIT"
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = ">=3.10,<3.12"
+faster-whisper = "^0.10.0"
+transformers = "^4.37.1"
+gradio = "^4.16.0"
+ruff = "^0.1.14"
+torch = "^2.1.2"
+
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^8.0.0"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"

src/sentiment.py

@@ -0,0 +1,18 @@
+""" 
+Get sentiment analysis results for the given text
+"""
+
+from transformers import pipeline
+
+sentiment_pipeline = pipeline(model="SamLowe/roberta-base-go_emotions")
+
+
+def analyze_sentiment(text: str) -> dict:
+    """Returns the sentiment analysis results for the given text"""
+    try:
+        results = sentiment_pipeline(text)
+        sentiment_results = {result["label"]: result["score"] for result in results}
+        return sentiment_results
+    except Exception as e:
+        print(f"Error in analyze_sentiment: {e}")
+        return {}

src/transcribe.py

@@ -0,0 +1,19 @@
+"""
+This module is used to transcribe the audio file and return the text
+"""
+
+from faster_whisper import WhisperModel
+
+
+model = WhisperModel("small", device="cpu", compute_type="int8")
+
+
+def transcribe_audio(audio_file: str) -> str:
+    """Returns the transcribed text and the sentiment analysis results"""
+    try:
+        segments, _ = model.transcribe(audio_file, beam_size=5)
+        text = list(segments)[0].text
+        return text
+    except Exception as e:
+        print(f"Error in transcribe_audio: {e}")
+        return ""

tests/test_sentiment.py

@@ -0,0 +1,33 @@
+from src.sentiment import analyze_sentiment
+
+
+def test_analyze_sentiment_positives():
+    # Positive sentiment
+    text = "I love this movie!"
+    expected_keys = ["love"]
+    result = analyze_sentiment(text)
+    assert all(key in result.keys() for key in expected_keys)
+
+
+def test_analyze_sentiment_negatives():
+    # Negative sentiment
+    text = "I hate this product!"
+    expected_keys = ["anger"]
+    result = analyze_sentiment(text)
+    assert all(key in result.keys() for key in expected_keys)
+
+
+def test_analyze_sentiment_empty():
+    # Negative sentiment
+    text = ""
+    expected_keys = ["neutral"]
+    result = analyze_sentiment(text)
+    assert all(key in result.keys() for key in expected_keys)
+
+
+def test_analyze_sentiment_neutral():
+    # Negative sentiment
+    text = "hello how are you"
+    expected_keys = ["neutral"]
+    result = analyze_sentiment(text)
+    assert all(key in result.keys() for key in expected_keys)

tests/test_transcribe.py

@@ -0,0 +1,18 @@
+import os
+from src.transcribe import transcribe_audio
+
+
+def test_transcribe_audio_success():
+    current_dir = os.path.dirname(os.path.abspath(__file__))
+    audio_file = os.path.join(current_dir, "samplings/thisisatest.mp3")
+    expected_text = "This is a test"
+    result = transcribe_audio(audio_file).strip().rstrip(".")
+    assert result == expected_text
+
+
+def test_transcribe_audio_failure():
+    # Transcription failure
+    audio_file = "samplings/nonexistent_audio.wav"
+    expected_text = ""
+    result = transcribe_audio(audio_file)
+    assert result == expected_text