File size: 2,982 Bytes
5f0a430 08654c0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
import logging
import sys
from fastapi import FastAPI, UploadFile, File, HTTPException
from pydantic import BaseModel
import config
from models import load_whisper, load_summarizer, load_spacy
from services import process_transcription, process_summary
logger = logging.getLogger(__name__)
app = FastAPI(
title="Transcription and Summarization API",
description="API using Faster-Whisper, spaCy, and Hugging Face Transformers",
version="1.0.0"
)
logger.info("Application starting up - loading models...")
whisper_model = load_whisper(config)
summarizer_pipeline = load_summarizer(config)
nlp_spacy = load_spacy(config)
logger.info("Model loading complete.")
if not whisper_model:
logger.critical("Whisper model failed to load. Transcription endpoint will be unavailable.")
if not summarizer_pipeline:
logger.critical("Summarizer pipeline failed to load. Summarization endpoint will be unavailable.")
if not nlp_spacy:
logger.warning("SpaCy model failed to load. Summarization will proceed without spaCy preprocessing.")
class TranscriptInput(BaseModel):
transcript: str
@app.get("/health")
def health():
return {"status": "ok",
"whisper_loaded": whisper_model is not None,
"summarizer_loaded": summarizer_pipeline is not None,
"spacy_loaded": nlp_spacy is not None
}
@app.post("/transcribe")
async def transcription(audio_file : UploadFile = File(...)):
if whisper_model is None:
raise HTTPException(status_code=503, detail="Transcription service unavailable.")
try:
content = await audio_file.read()
transcript, info = process_transcription(content, whisper_model)
logger.info(f"Transcription successful. Language: {info.language}")
return {"transcript": transcript}
except ValueError as ve:
logger.error(f"Value error during transcription processing: {ve}")
raise HTTPException(status_code=400, detail=str(ve))
except Exception as e:
logger.error(f"Unhandled error during transcription: {e}", exc_info=True)
raise HTTPException(status_code=500, detail="Internal server error during transcription.")
@app.post("/summarize")
def summarize(input: TranscriptInput):
if summarizer_pipeline is None:
raise HTTPException(status_code=503, detail="Summarization service unavailable.")
if not input.transcript:
raise HTTPException(status_code=400, detail="Transcript cannot be empty.")
try:
summary = process_summary(input.transcript, summarizer_pipeline, nlp_spacy, config)
return {"summary": summary}
except ValueError as ve:
logger.error(f"Value error during summary processing: {ve}")
raise HTTPException(status_code=400, detail=str(ve))
except Exception as e:
logger.error(f"Unhandled error during summarization: {e}", exc_info=True)
raise HTTPException(status_code=500, detail="Internal server error during summarization.") |