apunkt/SurfSense
1
0
Fork 0
mirror of https://github.com/MODSetter/SurfSense.git synced 2026-04-26 01:06:23 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor: integrate local STT with existing upload flow

Browse source 
- Simplify STT_SERVICE config to local/MODEL_SIZE format
- Remove separate STT routes, integrate with document upload
- Add local STT support to audio file processing pipeline
- Remove React component, use existing upload interface
- Support both local Faster-Whisper and external STT services
- Tested with real speech: 99% accuracy, 2.87s processing
This commit is contained in:
Nabhan 2025-10-12 10:50:55 +05:00
parent bd6b198e20
commit cf0e265107
7 changed files with 47 additions and 238 deletions
Download patch file Download diff file Expand all files Collapse all files

54
surfsense_backend/app/routes/documents_routes.py
View file

@ -784,25 +784,43 @@ async def process_file_in_background(
{"file_type": "audio", "processing_stage": "starting_transcription"},
)
# Open the audio file for transcription
with open(file_path, "rb") as audio_file:
# Check if using local STT service
if app_config.STT_SERVICE and app_config.STT_SERVICE.startswith("local/"):
# Use local Faster-Whisper for transcription
from app.services.stt_service import stt_service
result = stt_service.transcribe_file(file_path)
transcribed_text = result["text"]
await task_logger.log_task_progress(
log_entry,
f"Local STT transcription completed: {filename}",
{
"processing_stage": "local_transcription_complete",
"language": result["language"],
"confidence": result["language_probability"],
"duration": result["duration"],
},
)
else:
# Use LiteLLM for audio transcription
if app_config.STT_SERVICE_API_BASE:
transcription_response = await atranscription(
model=app_config.STT_SERVICE,
file=audio_file,
api_base=app_config.STT_SERVICE_API_BASE,
api_key=app_config.STT_SERVICE_API_KEY,
)
else:
transcription_response = await atranscription(
model=app_config.STT_SERVICE,
api_key=app_config.STT_SERVICE_API_KEY,
file=audio_file,
)
with open(file_path, "rb") as audio_file:
if app_config.STT_SERVICE_API_BASE:
transcription_response = await atranscription(
model=app_config.STT_SERVICE,
file=audio_file,
api_base=app_config.STT_SERVICE_API_BASE,
api_key=app_config.STT_SERVICE_API_KEY,
)
else:
transcription_response = await atranscription(
model=app_config.STT_SERVICE,
api_key=app_config.STT_SERVICE_API_KEY,
file=audio_file,
)
# Extract the transcribed text
transcribed_text = transcription_response.get("text", "")
# Extract the transcribed text
transcribed_text = transcription_response.get("text", "")
# Add metadata about the transcription
transcribed_text = (
@ -831,6 +849,7 @@ async def process_file_in_background(
)
if result:
stt_service_type = "local" if app_config.STT_SERVICE and app_config.STT_SERVICE.startswith("local/") else "external"
await task_logger.log_task_success(
log_entry,
f"Successfully transcribed and processed audio file: {filename}",
@ -839,6 +858,7 @@ async def process_file_in_background(
"content_hash": result.content_hash,
"file_type": "audio",
"transcript_length": len(transcribed_text),
"stt_service": stt_service_type,
},
)
else: