开源语音识别faster-whisper部署教程

1. 资源下载

���码地址

（）

模型下载地址：

large-v3模型：https://huggingface.co/Systran/faster-whisper-large-v3/tree/mainlarge-v2模型：https://huggingface.co/guillaumekln/faster-whisper-large-v2/tree/mainlarge-v2模型：https://huggingface.co/guillaumekln/faster-whisper-large-v1/tree/mainmedium模型：https://huggingface.co/guillaumekln/faster-whisper-medium/tree/mainsmall模型：https://huggingface.co/guillaumekln/faster-whisper-small/tree/mainbase模型：https://huggingface.co/guillaumekln/faster-whisper-base/tree/maintiny模型：https://huggingface.co/guillaumekln/faster-whisper-tiny/tree/main

下载cuBLAS and cuDNN

（）

https://github.com/Purfview/whisper-standalone-win/releases/tag/libs

2. 创建环境

在conda环境中创建python运行环境

conda create -n faster_whisper python=3.9 # python版本要求3.8到3.11

激活虚拟环境

conda activate faster_whisper

安装faster-whisper依赖

pip install faster-whisper

3. 运行

执行完以上步骤后，我们可以写代码了

from faster_whisper import WhisperModelmodel_size = "large-v3"path = r"D:\Works\Python\Faster_Whisper\model\small"# Run on GPU with FP16model = WhisperModel(model_size_or_path=path, device="cuda", local_files_only=True)# or run on GPU with INT8# model = WhisperModel(model_size, device="cuda", compute_type="int8_float16")# or run on CPU with INT8# model = WhisperModel(model_size, device="cpu", compute_type="int8")segments, info = model.transcribe("C:\Users\21316\Documents\录音\test.wav", beam_size=5, language="zh", vad_filter=True, vad_parameters=dict(min_silence_duration_ms=1000))print("Detected language '%s' with probability %f" % (info.language, info.language_probability))for segment in segments:    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

说明：

local_files_only=True 表示加载本地模型model_size_or_path=path 指定加载模型路径device="cuda" 指定使用cudacompute_type="int8_float16" 量化为8位language="zh" 指定音频语言vad_filter=True 开启vadvad_parameters=dict(min_silence_duration_ms=1000) 设置vad参数

更多内容欢迎访问博客

对应视频内容欢迎访问视频