使用 Faster-Whisper 实现本地实时语音转文本

# -*- coding: utf-8 -*-
import os
import sys
import time
import wave
import tempfile
import threading
import torch
import pyaudiowpatch as pyaudio
from faster_whisper import WhisperModel

# 录音切片时长（秒）
AUDIO_BUFFER = 5

def record_audio(p, device):
    # 创建临时文件
    with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as f:
        filename = f.name
        wave_file = wave.open(filename, "wb")
        wave_file.setnchannels(int(device["maxInputChannels"]))
        wave_file.setsampwidth(p.get_sample_size(pyaudio.paInt16))
        wave_file.setframerate(int(device["defaultSampleRate"]))

        def callback(in_data, frame_count, time_info, status):
            """写入音频帧"""
            wave_file.writeframes(in_data)
            return (in_data, pyaudio.paContinue)

        try:
            stream = p.open(format=pyaudio.paInt16, channels=int(device["maxInputChannels"]), rate=int(device["defaultSampleRate"]), frames_per_buffer=1024, input=True, input_device_index=device["index"], stream_callback=callback,)
            time.sleep(AUDIO_BUFFER)  # 阻塞主线程进行录音
        except Exception as e:
            print(f"录音出错：{e}")
        finally:
            if 'stream' in locals():
                stream.stop_stream()
                stream.close()
            wave_file.close()
        return filename

def whisper_audio(filename, model):
    """调用模型进行转录"""
    try:
        # vad_filter=True 可以去掉没说话的静音片段
        segments, info = model.transcribe(filename, beam_size=5, language="zh", vad_filter=True, vad_parameters=dict(min_silence_duration_ms=500))
        for segment in segments:
            print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
    except Exception as e:
        print(f"转录出错：{e}")
    finally:
        # 转录完成后删除临时文件
        if os.path.exists(filename):
            os.remove(filename)

def main():
    print("正在加载 Whisper 模型...")
    # 检查 GPU
    if torch.cuda.is_available():
        device = "cuda"
        compute_type = "float16"  # 或者 "int8_float16"
        print("使用 GPU (CUDA) 进行推理")
    else:
        device = "cpu"
        compute_type = "int8"  # CPU 上推荐用 int8
        print("使用 CPU 进行推理")

    # 模型路径
    model_path = "large-v3"
    try:
        model = WhisperModel(model_path, device=device, compute_type=compute_type, local_files_only=True)
        print("模型加载成功！")
    except Exception as e:
        print(f"模型加载失败：{e}")
        return

    with pyaudio.PyAudio() as p:
        try:
            default_mic = p.get_default_input_device_info()
            print(f"\n当前使用的麦克风：{default_mic['name']} (Index: {default_mic['index']})")
            print(f"采样率：{default_mic['defaultSampleRate']}, 通道数：{default_mic['maxInputChannels']}")
            print("-" * 50)
            print("开始持续录音 (按 Ctrl+C 停止)...")
            while True:
                filename = record_audio(p, default_mic)
                thread = threading.Thread(target=whisper_audio, args=(filename, model))
                thread.start()
        except OSError:
            print("未找到默认麦克风，请检查系统声音设置。")
        except KeyboardInterrupt:
            print("\n停止录音，程序退出。")
        except Exception as e:
            print(f"\n发生未知错误：{e}")

if __name__ == '__main__':
    main()

3. 报错解决方法

报错： Could not locate cudnn_ops64_9.dll. Please make sure it is in your library path! Invalid handle. Cannot load symbol cudnnCreateTensorDescriptor

Faster-Whisper 所依赖的 CTranslate2 引擎是基于 cuDNN 9.x 版本编译的，如果电脑上没有找到 cuDNN v9，可以尝试安装旧版本：

pip install --force-reinstall ctranslate2==4.4.0

如果还是报错，可能是 CUDA 版本问题。找到你的 CUDA 安装在其他位置，例如 C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.3\bin。 找到 cublas64_11.dll，复制出来，改成 cublas64_12.dll。

如果使用 CUDA 11.8 时报错 cuBLAS failed with status CUBLAS_STATUS_NOT_SUPPORTED，这是因为 PyTorch 自带 CUDA 11.8，但虚拟环境可能没有对应的 cublas64_12.dll。操作同上，找到虚拟环境中 torch\lib 下的 cublas64_11.dll，复制一份并改名为 cublas64_12.dll。

报错： Applying the VAD filter requires the onnxruntime package 将 onnxruntime 库版本降低即可，例如安装 1.19.2：

pip install onnxruntime==1.19.2

总结

通过以上步骤，即可完成 Faster-Whisper 的本地部署与实时语音转文本功能的实现。