panlr/

whisper-finetune-teochew

若用【个】表示【的】，那么【有个人】，究竟是【有一个人】，还是【有的人】呢？ 因此本数据集用【介】代替【个】。
若用【只】表示【这】，那么【这只猫】、【这只车】，便会写成【只只猫】、【只只车】，看起来非常怪异，因此本数据集用繁异字【祇】表示【这】之意，其他情况同普通话。

安装依赖：
pip install -r requirements.txt

from transformers import pipeline
device = "cuda:0" if torch.cuda.is_available() else "cpu"

# 创建识别管道
pipe = pipeline(
    "automatic-speech-recognition",
    model="panlr/whisper-finetune-teochew",
    device=device
)
# 识别音频
result = pipe("example.wav")
print(result["text"])

import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline

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

# 加载模型
model = AutoModelForSpeechSeq2Seq.from_pretrained(
    "panlr/whisper-finetune-teochew",
    torch_dtype=torch_dtype,
    low_cpu_mem_usage=True,
    use_safetensors=True
)
model.to(device)

# 加载处理器
processor = AutoProcessor.from_pretrained("panlr/whisper-finetune-teochew")

# 创建推理管道
pipe = pipeline(
    "automatic-speech-recognition",
    model=model,
    tokenizer=processor.tokenizer,
    feature_extractor=processor.feature_extractor,
    torch_dtype=torch_dtype,
    device=device,
)

# 执行识别
result = pipe("example.wav")
print(result["text"])

    python inference.py audio.wav
    python inference.py audio.wav --model panlr/whisper-finetune-teochew
    python inference.py audio.wav --cpu
    python inference.py audio1.wav audio2.wav audio3.wav --output result.txt