FASR: Fast Automatic Speech Recognition
Project description
🪐 项目: fasr
Fast Auto Speech Recognition
📋 简介
fasr是一款快速且易于使用的python库,它源于FunASR,专注于推理性能,目标是成为一个工业级别的python语音识别推理库。
📋 安装
wpai
- 在wpai平台选择pytorch镜像后,执行以下命令安装所有依赖
bash install.sh
本地
pip install poetry
poetry build
pip install dist/fasr-xxx-tar.gz
📋 使用
- 下载模型
fasr prepare
- 构建pipeline
from fasr import ASR
# 语音识别pipeline
asr = ASR().add_pipe('loader').add_pipe('detector').add_pipe('recognizer').add_pipe('sentencizer')
# 准备音频地址
urls = get_urls()
# 运行
audios = asr.run(urls)
# 打印结果
for audio in audios:
for channel in audio.channels:
print(channel.text)
- benchmark
# 准备音频地址urls.txt
fasr benchmark pipeline ./urls.txt
fasr benchmark vad ./urls.txt
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
fasr-0.1.3.tar.gz
(36.4 kB
view hashes)
Built Distribution
fasr-0.1.3-py3-none-any.whl
(45.0 kB
view hashes)