local_hf_whisper

local_hf_whisper.py

import torch
from transformers import pipeline

device = "cuda:0" if torch.cuda.is_available() else "cpu"
mapping = {"whisper-tiny" : "tiny", "whisper-small" : "small", "whisper-medium" : "medium", "whisper-base" : "base"}

hf_model_name = "whisper-medium"
size_model = mapping[hf_model_name] #tiny, base, small, medium

model = pipeline(
  "automatic-speech-recognition",
  model=f"openai/{hf_model_name}",
  chunk_length_s=30,
  device=device,
)

def get_transcript_local_whisper_hf(model, file, language="french"):
    return model(file, generate_kwargs={"language": language})["text"]
  
transcript = get_transcript_local_whisper_hf(model, file)