前言
要实现类似豆包、微信的语音输入功能,通常有两种主流方案:云端 API(轻量、准确度极高)和本地模型(免费、隐私、无需联网)。本文记录使用 Faster-Whisper 实现本地实时语音输入转文本的部署过程。
电脑有显卡的话可以参考相关教程安装 CUDA 和 cuDNN。
一、安装环境
在虚拟环境中安装 faster-whisper:
pip install faster-whisper
安装录音库:
pip install pyaudio
二、使用步骤
1. 下载模型
手动下载(离线使用):如果服务器无法联网或需指定文件夹,可手动下载。根据需求选择模型版本:
- Tiny (最小/最快)
- Base
- Small
- Medium
- Large-v2
- Large-v3 (效果最好)
- Distil-Large-v3 (蒸馏版/速度快)
在 Hugging Face 的 "Files and versions" 页面中,下载以下关键文件并放入同一文件夹:
config.jsonmodel.bintokenizer.jsonvocabulary.jsonpreprocessor_config.json
2. 实时录音转文本脚本
代码如下:
# -*- coding: utf-8 -*-
import os
import sys
import time
import wave
import tempfile
import threading
import torch
import 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[]))
wave_file.setsampwidth(p.get_sample_size(pyaudio.paInt16))
wave_file.setframerate((device[]))
():
wave_file.writeframes(in_data)
(in_data, pyaudio.paContinue)
:
stream = p.(=pyaudio.paInt16,
channels=(device[]),
rate=(device[]),
frames_per_buffer=,
=,
input_device_index=device[],
stream_callback=callback,)
time.sleep(AUDIO_BUFFER)
Exception e:
()
:
():
stream.stop_stream()
stream.close()
wave_file.close()
filename
():
:
segments, info = model.transcribe(
filename,
beam_size=,
language=,
vad_filter=,
vad_parameters=(min_silence_duration_ms=)
)
segment segments:
( % (segment.start, segment.end, segment.text))
Exception e:
()
:
os.path.exists(filename):
os.remove(filename)
():
()
torch.cuda.is_available():
device =
compute_type =
()
:
device =
compute_type =
()
model_path =
:
model = WhisperModel(model_path, device=device, compute_type=compute_type, local_files_only=)
()
Exception e:
()
pyaudio.PyAudio() p:
:
default_mic = p.get_default_input_device_info()
()
()
( * )
()
:
filename = record_audio(p, default_mic)
thread = threading.Thread(target=whisper_audio, args=(filename, model))
thread.start()
OSError:
()
KeyboardInterrupt:
()
Exception e:
()
__name__ == :
main()


