feat: add voice recognition

2026-03-28 20:00:48 +08:00
parent 27270063f7
commit c983829392
7 changed files with 695 additions and 70 deletions
@@ -0,0 +1,210 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+data
+*.db
+
+# 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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# 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
+.envrc
+.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/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
@@ -0,0 +1,39 @@
+# Whisper Transcription Service
+
+This is a standalone HTTP service for transcribing audio files using the OpenAI Whisper model.
+
+## Prerequisites
+
+Make sure you have Python 3.9+ and `ffmpeg` installed on your system.
+
+To install `ffmpeg` on macOS:
+```bash
+brew install ffmpeg
+```
+
+## Setup & Run
+
+1. Create a virtual environment and install dependencies:
+```bash
+cd whisper
+python -m venv .venv
+source .venv/bin/activate
+pip install -r requirements.txt
+```
+
+2. Start the server:
+```bash
+python main.py
+```
+Or run with uvicorn directly:
+```bash
+uvicorn main:app --host 0.0.0.0 --port 8001 --reload
+```
+
+The service will run on `http://localhost:8001`.
+
+## API Endpoint
+
+- `POST /transcribe`
+  - Body: `multipart/form-data` with a `file` field containing the audio blob.
+  - Returns: `{"text": "transcribed text..."}`
@@ -0,0 +1,71 @@
+import os
+import shutil
+import ssl
+import tempfile
+import traceback
+from fastapi import FastAPI, File, UploadFile
+from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import JSONResponse
+import whisper
+import imageio_ffmpeg
+
+# Ensure whisper can execute "ffmpeg" command
+_ffmpeg_exe = imageio_ffmpeg.get_ffmpeg_exe()
+_ffmpeg_bin_dir = os.path.join(tempfile.gettempdir(), "dataclaw_ffmpeg_bin")
+_ffmpeg_link = os.path.join(_ffmpeg_bin_dir, "ffmpeg")
+os.makedirs(_ffmpeg_bin_dir, exist_ok=True)
+if not os.path.exists(_ffmpeg_link):
+    try:
+        os.symlink(_ffmpeg_exe, _ffmpeg_link)
+    except OSError:
+        shutil.copy2(_ffmpeg_exe, _ffmpeg_link)
+        os.chmod(_ffmpeg_link, 0o755)
+os.environ["PATH"] = _ffmpeg_bin_dir + os.pathsep + os.environ.get("PATH", "")
+
+# Disable SSL verification temporarily to fix UNEXPECTED_EOF_WHILE_READING error during model download
+ssl._create_default_https_context = ssl._create_unverified_context
+
+app = FastAPI(title="Whisper Transcription Service")
+
+# Allow CORS for frontend
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # Allows all origins
+    allow_credentials=True,
+    allow_methods=["*"],  # Allows all methods
+    allow_headers=["*"],  # Allows all headers
+)
+
+# Load the whisper model globally. "small" is a good balance between speed and accuracy.
+print("Loading Whisper model (small)... This may take a moment.")
+model = whisper.load_model("small")
+print("Model loaded successfully.")
+
+@app.post("/transcribe")
+async def transcribe_audio(file: UploadFile = File(...)):
+    # Save the uploaded file to a temporary file
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".webm") as tmp:
+        content = await file.read()
+        tmp.write(content)
+        tmp_path = tmp.name
+
+    try:
+        # Convert webm to wav since Whisper's internal ffmpeg dependency can be problematic
+        # We will use an alternative approach or just pass the webm if it works natively
+        
+        # Transcribe using whisper
+        # Forcing language to Chinese for better accuracy on Chinese speech
+        result = model.transcribe(tmp_path, language="zh", task="transcribe")
+        return {"text": result.get("text", "")}
+    except Exception as e:
+        print(f"Error during transcription: {e}")
+        print(traceback.format_exc())
+        return JSONResponse(status_code=500, content={"error": str(e)})
+    finally:
+        # Clean up the temporary file
+        if os.path.exists(tmp_path):
+            os.remove(tmp_path)
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8001)
@@ -0,0 +1,4 @@
+fastapi
+uvicorn
+python-multipart
+openai-whisper