本篇博客旨在记录自己学习大语言模型的过程

基于Whisper实现音频转文本

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
import os
os.environ['TF_ENABLE_ONEDNN_OPTS'] = '0'

import warnings
warnings.filterwarnings("ignore", category=DeprecationWarning)

import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline

device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

model_id = "openai/whisper-large-v3-turbo"

model = AutoModelForSpeechSeq2Seq.from_pretrained(
    model_id, torch_dtype=torch_dtype, 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,
    torch_dtype=torch_dtype,
    device=device,
)

# dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
#whisper-large-v3-turbo模型是一个强大的音频自动识别转文本模型（支持多语言）
result = pipe(["test1.wav", "test.wav"], batch_size=2)

print(result[0]["text"])
print(result[1]["text"])

(新手第一次写博客，如有错误和不好的地方，请多担待，另外对程序有问题请提出噢！)