Spaces:
Sleeping
Sleeping
File size: 1,404 Bytes
629adbe 94b73ef 629adbe e6dcb8a 629adbe 94b73ef 629adbe e6dcb8a 629adbe 94b73ef |
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 |
import torch
import requests
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
from datasets import load_dataset
from pydantic import BaseModel
from fastapi import FastAPI
class URLPayload(BaseModel):
url: str
app = FastAPI()
def process_audio(url: str):
response = requests.get(url)
with open("/tmp/audio.mp3", mode="wb") as file:
file.write(response.content)
device = "cpu"
model_id = "openai/whisper-large-v3"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id, torch_dtype=torch.float32, low_cpu_mem_usage=True, use_safetensors=True
)
model.to(device)
processor = AutoProcessor.from_pretrained(model_id)
pipe = pipeline(
"automatic-speech-recognition",
model=model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
max_new_tokens=8192,
chunk_length_s=30,
batch_size=16,
return_timestamps=True,
torch_dtype=torch.float32,
device=device
)
dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
whisper_result = pipe("/tmp/audio.mp3")
return whisper_result
@app.post("/process/")
async def process_audio_endpoint(payload: URLPayload):
result = process_audio(payload.url)
return result
|