许可证：MIT
数据集：

• mozilla-foundation/common_voice_11_0
  语言：
• 波斯语（fa）
  评估指标：
• 词错误率（wer）
  基础模型：
• openai/whisper-large-v3-turbo
  任务标签：自动语音识别
  库名称：transformers
  标签：
• 医疗

训练损失：0.013100
验证损失：0.043175
训练轮次：1

如何在Colab中使用该模型：

# 安装必要包
!pip install torch torchaudio transformers pydub google-colab

import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
from pydub import AudioSegment
import os
from google.colab import files

# 加载模型和处理器
model_id = "hackergeek98/whisper-persian-turbooo"
device = "cuda" if torch.cuda.is_available() else "cpu"

model = AutoModelForSpeechSeq2Seq.from_pretrained(model_id).to(device)
processor = AutoProcessor.from_pretrained(model_id)

# 创建处理管道
whisper_pipe = pipeline(
    "automatic-speech-recognition", 
    model=model, 
    tokenizer=processor.tokenizer, 
    feature_extractor=processor.feature_extractor, 
    device=0 if torch.cuda.is_available() else -1
)

# 将音频转换为WAV格式
def convert_to_wav(audio_path):
    audio = AudioSegment.from_file(audio_path)
    wav_path = "converted_audio.wav"
    audio.export(wav_path, format="wav")
    return wav_path

# 分割长音频为片段（默认每段30秒）
def split_audio(audio_path, chunk_length_ms=30000):
    audio = AudioSegment.from_wav(audio_path)
    chunks = [audio[i:i+chunk_length_ms] for i in range(0, len(audio), chunk_length_ms)]
    chunk_paths = []
    
    for i, chunk in enumerate(chunks):
        chunk_path = f"chunk_{i}.wav"
        chunk.export(chunk_path, format="wav")
        chunk_paths.append(chunk_path)
    
    return chunk_paths

# 转录长音频文件
def transcribe_long_audio(audio_path):
    wav_path = convert_to_wav(audio_path)
    chunk_paths = split_audio(wav_path)
    transcription = ""
    
    for chunk in chunk_paths:
        result = whisper_pipe(chunk)
        transcription += result["text"] + "\n"
        os.remove(chunk)  # 删除已处理片段
    
    os.remove(wav_path)  # 清理原始文件
    
    # 将转录结果保存到文本文件
    text_path = "transcription.txt"
    with open(text_path, "w") as f:
        f.write(transcription)
    
    return text_path

# 在Colab中上传并处理音频
uploaded = files.upload()
audio_file = list(uploaded.keys())[0]
transcription_file = transcribe_long_audio(audio_file)

# 下载转录文件
files.download(transcription_file)