first commit

.gitignore

@@ -0,0 +1,165 @@
+# Custom
+*.mp3
+*.wav
+temp/
+
+# 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/

app.py

@@ -0,0 +1,111 @@
+# Import the required libraries
+import streamlit as st
+import whisper
+import speech_recognition as sr
+from pydub import AudioSegment
+import os
+import sounddevice as sd
+import numpy as np
+from scipy.io.wavfile import write
+import os 
+
+
+# Function to transcribe audio using OpenAI Whisper
+def transcribe_whisper(model_name, file_path):
+    model = whisper.load_model(model_name)
+    result = model.transcribe(file_path)
+    return result["text"]
+
+# Function to transcribe audio using Google Speech API
+def transcribe_speech_recognition(file_path):
+    r = sr.Recognizer()
+    with sr.AudioFile(file_path) as source:
+        r.adjust_for_ambient_noise(source, duration=0.5)  # Adjust ambient noise threshold
+        audio = r.record(source)
+
+    try:
+        result = r.recognize_google(audio, language='es')
+        return result
+    except sr.UnknownValueError:
+        return "No se pudo reconocer ningún texto en el audio."
+
+# Function to convert mp3 file to wav
+def convert_mp3_to_wav(mp3_path):
+    audio = AudioSegment.from_mp3(mp3_path)
+    wav_path = mp3_path.replace('.mp3', '.wav')
+    audio.export(wav_path, format="wav")
+    return wav_path
+
+# Function to record audio
+def record_audio(filename, duration):
+    fs = 44100  # Sample rate
+    channels = 2  # Number of channels (1 for mono, 2 for stereo)
+    
+    # Start recording
+    recording = sd.rec(int(duration * fs), samplerate=fs, channels=channels)
+    sd.wait()  # Wait until recording is finished
+    # Create temp directory if it doesn't exist
+    if not os.path.exists(os.path.dirname(filename)):
+        os.makedirs(os.path.dirname(filename))
+
+    # Save as WAV file
+    write(filename, fs, recording)
+
+def main():
+    st.title('Transcriptor de Audio')
+
+    # Choose the transcription method and model
+    transcription_method = st.selectbox('Escoge el método de transcripción', ('OpenAI Whisper', 'Google Speech API'))
+    if transcription_method == 'OpenAI Whisper':
+        model_name = st.selectbox('Escoge el modelo de Whisper', ('base', 'small', 'medium', 'large', 'tiny'))
+
+    option = st.selectbox('Escoge la opción', ('Subir un archivo', 'Grabar audio en tiempo real'))
+
+    if option == 'Subir un archivo':
+        uploaded_file = st.file_uploader("Sube tu archivo de audio para transcribir", type=['wav', 'mp3'])
+
+        if uploaded_file is not None:
+            file_details = {"FileName": uploaded_file.name, "FileType": uploaded_file.type, "FileSize": uploaded_file.size}
+            st.write(file_details)
+
+            # Save uploaded file to temp directory
+            file_path = os.path.join("temp", uploaded_file.name)
+            with open(file_path, "wb") as f:
+                f.write(uploaded_file.getbuffer())
+
+            st.write("Archivo de audio cargado correctamente. Transcribiendo...")
+            with st.spinner('Transcribiendo...'):
+                if uploaded_file.name.endswith('.mp3') and transcription_method != 'OpenAI Whisper':
+                    # Convert mp3 to wav if Google Speech API is selected and file is in mp3 format
+                    file_path = convert_mp3_to_wav(file_path)
+
+                # Perform transcription
+                if transcription_method == 'OpenAI Whisper':
+                    transcript = transcribe_whisper(model_name, file_path)
+                else:
+                    transcript = transcribe_speech_recognition(file_path)
+
+                st.text_area('Resultado de la Transcripción:', transcript, height=200)
+    
+    elif option == 'Grabar audio en tiempo real':
+        duration = st.slider("Selecciona la duración de la grabación (segundos)", 1, 10, 5)
+        start_recording = st.button('Empezar a grabar')
+
+        if start_recording:
+            filename = "temp/recorded_audio.wav"
+            st.write("Grabación en progreso...")
+            with st.spinner('Grabando...'):
+                record_audio(filename, duration)
+            
+            st.write("Grabación finalizada. Transcribiendo...")
+            with st.spinner('Transcribiendo...'):
+                # Perform transcription
+                if transcription_method == 'OpenAI Whisper':
+                    transcript = transcribe_whisper(model_name, filename)
+                else:
+                    transcript = transcribe_speech_recognition(filename)
+
+                st.text_area('Resultado de la Transcripción:', transcript, height=200)
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,8 @@
+sounddevice
+numpy
+scipy
+pydub
+streamlit
+python-dotenv
+whisper-openai
+SpeechRecognition