dillon_stuff/TalkEdit
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases 1 Wiki Activity

changed to python312

Browse Source
This commit is contained in:
dillonj
2026-03-28 12:26:45 -06:00
parent 4a857d8cbf
commit 2ffc406b10
9 changed files with 443 additions and 64 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
backend/main.py
View File

@ -61,18 +61,37 @@ async def serve_local_file(request: Request, path: str = Query(...)):
"""Stream a local file with HTTP Range support (required for video seeking)."""
file_path = Path(path)
if not file_path.is_file():
logger.warning(f"[serve_file] File not found: {path}")
raise HTTPException(status_code=404, detail=f"File not found: {path}")
file_size = file_path.stat().st_size
content_type = MIME_MAP.get(file_path.suffix.lower(), "application/octet-stream")
range_header = request.headers.get("range")
logger.info(
f"[serve_file] {file_path.name} | size={file_size} | "
f"type={content_type} | range={range_header or 'none'}"
)
if content_type == "application/octet-stream":
logger.warning(
f"[serve_file] Unknown MIME type for extension '{file_path.suffix}' — "
f"browser may fail to decode audio/video for '{file_path.name}'"
)
if file_size == 0:
logger.error(f"[serve_file] File is empty: {path}")
raise HTTPException(status_code=422, detail=f"File is empty: {path}")
if range_header:
range_spec = range_header.replace("bytes=", "")
range_start_str, range_end_str = range_spec.split("-")
range_start = int(range_start_str) if range_start_str else 0
range_end = int(range_end_str) if range_end_str else file_size - 1
range_end = min(range_end, file_size - 1)
try:
range_spec = range_header.replace("bytes=", "")
range_start_str, range_end_str = range_spec.split("-")
range_start = int(range_start_str) if range_start_str else 0
range_end = int(range_end_str) if range_end_str else file_size - 1
range_end = min(range_end, file_size - 1)
except (ValueError, TypeError) as e:
logger.error(f"[serve_file] Malformed Range header '{range_header}': {e}")
raise HTTPException(status_code=416, detail=f"Invalid Range header: {range_header}")
content_length = range_end - range_start + 1
def iter_range():

197
backend/requirements.txt
View File

@ -1,33 +1,164 @@
# FastAPI backend
fastapi>=0.115.0
uvicorn[standard]>=0.32.0
websockets>=14.0
python-multipart>=0.0.12
# Transcription (WhisperX for word-level alignment)
whisperx>=3.1.0
faster-whisper>=1.0.0
# Audio / Video processing
moviepy>=1.0.3
ffmpeg-python>=0.2.0
soundfile>=0.10.3
# ML / GPU
torch>=2.0.0
torchaudio>=2.0.0
numpy>=1.24.0
# Speaker diarization
pyannote.audio>=3.1.1
# AI providers
openai>=1.50.0
anthropic>=0.39.0
requests>=2.28.0
# Audio cleanup
deepfilternet>=0.5.0
# Utilities
pydantic>=2.0.0
aiohappyeyeballs==2.6.1
aiohttp==3.13.4
aiosignal==1.4.0
alembic==1.18.4
annotated-doc==0.0.4
annotated-types==0.7.0
anthropic==0.86.0
antlr4-python3-runtime==4.9.3
anyio==4.13.0
appdirs==1.4.4
asteroid-filterbanks==0.4.0
attrs==26.1.0
av==17.0.0
certifi==2026.2.25
cffi==2.0.0
charset-normalizer==3.4.6
click==8.3.1
colorlog==6.10.1
contourpy==1.3.3
ctranslate2==4.7.1
cuda-bindings==12.9.4
cuda-pathfinder==1.2.2
cuda-toolkit==12.6.3
cycler==0.12.1
Cython==0.29.37
decorator==5.2.1
DeepFilterLib==0.5.6
DeepFilterNet==0.5.6
distro==1.9.0
docstring_parser==0.17.0
einops==0.8.2
fastapi==0.135.2
faster-whisper==1.2.1
ffmpeg-python==0.2.0
filelock==3.25.2
flatbuffers==25.12.19
fonttools==4.62.1
frozenlist==1.8.0
fsspec==2026.2.0
future==1.0.0
googleapis-common-protos==1.73.1
greenlet==3.3.2
grpcio==1.78.0
h11==0.16.0
hf-xet==1.4.2
httpcore==1.0.9
httptools==0.7.1
httpx==0.28.1
huggingface_hub==0.36.2
HyperPyYAML==1.2.3
idna==3.11
ImageIO==2.37.3
imageio-ffmpeg==0.6.0
importlib_metadata==8.7.1
Jinja2==3.1.6
jiter==0.13.0
joblib==1.5.3
julius==0.2.7
kiwisolver==1.5.0
lightning==2.6.1
lightning-utilities==0.15.3
loguru==0.7.3
Mako==1.3.10
markdown-it-py==4.0.0
MarkupSafe==3.0.3
matplotlib==3.10.8
maturin==1.12.6
mdurl==0.1.2
moviepy==2.2.1
mpmath==1.3.0
multidict==6.7.1
networkx==3.6.1
nltk==3.9.4
numpy==2.4.3
nvidia-cublas-cu12==12.8.4.1
nvidia-cuda-cupti-cu12==12.8.90
nvidia-cuda-nvrtc-cu12==12.8.93
nvidia-cuda-runtime-cu12==12.8.90
nvidia-cudnn-cu12==9.10.2.21
nvidia-cufft-cu12==11.3.3.83
nvidia-cufile-cu12==1.13.1.3
nvidia-curand-cu12==10.3.9.90
nvidia-cusolver-cu12==11.7.3.90
nvidia-cusparse-cu12==12.5.8.93
nvidia-cusparselt-cu12==0.7.1
nvidia-nccl-cu12==2.27.3
nvidia-nvjitlink-cu12==12.8.93
nvidia-nvshmem-cu12==3.4.5
nvidia-nvtx-cu12==12.8.90
omegaconf==2.3.0
onnxruntime==1.24.4
openai==2.30.0
opentelemetry-api==1.40.0
opentelemetry-exporter-otlp==1.40.0
opentelemetry-exporter-otlp-proto-common==1.40.0
opentelemetry-exporter-otlp-proto-grpc==1.40.0
opentelemetry-exporter-otlp-proto-http==1.40.0
opentelemetry-proto==1.40.0
opentelemetry-sdk==1.40.0
opentelemetry-semantic-conventions==0.61b0
optuna==4.8.0
packaging==23.2
pandas==3.0.1
pillow==11.3.0
primePy==1.3
proglog==0.1.12
propcache==0.4.1
protobuf==6.33.6
pyannote-audio==4.0.4
pyannote-core==6.0.1
pyannote-database==6.1.1
pyannote-metrics==4.0.0
pyannote-pipeline==4.0.0
pyannoteai-sdk==0.4.0
pycparser==3.0
pydantic==2.12.5
pydantic_core==2.41.5
Pygments==2.19.2
pyparsing==3.3.2
python-dateutil==2.9.0.post0
python-dotenv==1.2.2
python-multipart==0.0.22
pytorch-lightning==2.6.1
pytorch-metric-learning==2.9.0
PyYAML==6.0.3
regex==2026.2.28
requests==2.33.0
rich==14.3.3
ruamel.yaml==0.18.17
ruamel.yaml.clib==0.2.15
safetensors==0.7.0
scikit-learn==1.8.0
scipy==1.17.1
setuptools==70.2.0
shellingham==1.5.4
six==1.17.0
sniffio==1.3.1
sortedcontainers==2.4.0
soundfile==0.13.1
SQLAlchemy==2.0.48
starlette==1.0.0
sympy==1.14.0
threadpoolctl==3.6.0
tokenizers==0.22.2
torch==2.8.0
torch-audiomentations==0.12.0
torch_pitch_shift==1.2.5
torchaudio==2.8.0
torchmetrics==1.9.0
tqdm==4.67.3
transformers==4.57.6
triton==3.4.0
typer==0.24.1
typing-inspection==0.4.2
typing_extensions==4.15.0
urllib3==2.6.3
uvicorn==0.42.0
uvloop==0.22.1
watchfiles==1.1.1
websockets==16.0
wheel==0.46.3
whisperx==3.8.4
yarl==1.23.0
zipp==3.23.0

65
backend/routers/audio.py
View File

@ -1,9 +1,14 @@
"""Audio processing endpoint (noise reduction / Studio Sound)."""
import hashlib
import logging
import subprocess
import tempfile
from pathlib import Path
from typing import Optional
from fastapi import APIRouter, HTTPException
from fastapi import APIRouter, HTTPException, Query
from fastapi.responses import FileResponse
from pydantic import BaseModel
from services.audio_cleaner import clean_audio, is_deepfilter_available
@ -11,6 +16,9 @@ from services.audio_cleaner import clean_audio, is_deepfilter_available
logger = logging.getLogger(__name__)
router = APIRouter()
# Simple in-process cache: video path → extracted WAV path
_waveform_cache: dict[str, str] = {}
class AudioCleanRequest(BaseModel):
input_path: str
@ -36,3 +44,58 @@ async def audio_capabilities():
return {
"deepfilternet_available": is_deepfilter_available(),
}
@router.get("/audio/waveform")
async def get_waveform_audio(path: str = Query(...)):
"""
Extract audio from any video/audio file and return it as a WAV.
The WAV is cached on disk for subsequent requests.
Uses FFmpeg directly so it works with MKV, MOV, AVI, MP4, etc.
"""
file_path = Path(path)
if not file_path.is_file():
logger.warning(f"[waveform] File not found: {path}")
raise HTTPException(status_code=404, detail=f"File not found: {path}")
# Cache key based on path + mtime so stale cache is auto-invalidated
mtime = file_path.stat().st_mtime
cache_key = hashlib.md5(f"{path}:{mtime}".encode()).hexdigest()
if cache_key in _waveform_cache:
cached = Path(_waveform_cache[cache_key])
if cached.exists():
logger.info(f"[waveform] Cache hit for {file_path.name}")
return FileResponse(str(cached), media_type="audio/wav")
else:
del _waveform_cache[cache_key]
logger.info(f"[waveform] Extracting audio from: {file_path.name}")
tmp_dir = tempfile.mkdtemp(prefix="talkedit_waveform_")
out_wav = Path(tmp_dir) / f"{cache_key}.wav"
# Downsample to mono 22050 Hz — enough for waveform drawing, small file
cmd = [
"ffmpeg", "-y",
"-i", str(file_path),
"-vn", # drop video
"-ac", "1", # mono
"-ar", "22050", # 22 kHz sample rate
"-acodec", "pcm_s16le", # 16-bit PCM WAV
str(out_wav),
]
result = subprocess.run(cmd, capture_output=True, text=True)
if result.returncode != 0:
logger.error(f"[waveform] FFmpeg failed for {file_path.name}: {result.stderr[-500:]}")
raise HTTPException(
status_code=500,
detail=f"Failed to extract audio: {result.stderr[-300:]}"
)
if not out_wav.exists() or out_wav.stat().st_size == 0:
logger.error(f"[waveform] FFmpeg produced empty WAV for {file_path.name}")
raise HTTPException(status_code=500, detail="Audio extraction produced empty file")
logger.info(f"[waveform] Extracted {out_wav.stat().st_size} bytes for {file_path.name}")
_waveform_cache[cache_key] = str(out_wav)
return FileResponse(str(out_wav), media_type="audio/wav")

17
backend/utils/audio_processing.py
View File

@ -15,8 +15,13 @@ _temp_audio_files = []
def extract_audio(video_path: Path):
"""Extract audio from a video file into a temp directory for automatic cleanup."""
logger.info(f"[extract_audio] Extracting audio from: {video_path}")
try:
audio = AudioFileClip(str(video_path))
if audio.duration is None or audio.duration == 0:
logger.error(f"[extract_audio] File has no audio track or zero duration: {video_path}")
raise RuntimeError(f"File has no audio track: {video_path}")
logger.info(f"[extract_audio] Duration: {audio.duration:.2f}s, fps: {audio.fps}")
temp_dir = tempfile.mkdtemp(prefix="videotranscriber_")
audio_path = Path(temp_dir) / f"{video_path.stem}_audio.wav"
try:
@ -25,9 +30,16 @@ def extract_audio(video_path: Path):
# moviepy 1.x uses verbose parameter; moviepy 2.x removed it
audio.write_audiofile(str(audio_path), verbose=False, logger=None)
audio.close()
if not audio_path.exists() or audio_path.stat().st_size == 0:
logger.error(f"[extract_audio] Output WAV is empty or missing: {audio_path}")
raise RuntimeError(f"Audio extraction produced empty file: {audio_path}")
logger.info(f"[extract_audio] Extracted to: {audio_path} ({audio_path.stat().st_size} bytes)")
_temp_audio_files.append(str(audio_path))
return audio_path
except RuntimeError:
raise
except Exception as e:
logger.error(f"[extract_audio] Failed for '{video_path}': {e}", exc_info=True)
raise RuntimeError(f"Audio extraction failed: {e}")
@ -54,6 +66,9 @@ def get_video_duration(video_path: Path):
clip = AudioFileClip(str(video_path))
duration = clip.duration
clip.close()
if duration is None or duration == 0:
logger.warning(f"[get_video_duration] Zero or null duration for: {video_path}")
return duration
except Exception:
except Exception as e:
logger.error(f"[get_video_duration] Failed for '{video_path}': {e}", exc_info=True)
return None