Skip to main content

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。

文档地址

📋 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

fasr可以通过直接通过pip安装,但是如果需要使用gpu,需要安装pytorch和onnxruntime-gpu

  • 安装pytorch: 通过官网安装对应cuda版本
  • 安装onnxruntime-gpu: 通过官网安装对应cuda版本
  • 安装fasr
pip install fasr

📋 使用

  • 下载模型
fasr prepare
  • 构建pipeline
from fasr import AudioPipeline

# 语音识别pipeline
asr = AudioPipeline().add_pipe('detector').add_pipe('recognizer').add_pipe('sentencizer')

# 准备音频数据url或者本地路径
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)

📋 性能测试

双通道音频

vad->asr->punc

测试结果

cpu: Intel(R) Xeon(R) Silver 4210 CPU @ 2.20GHz (wpai cpu 2核)

gpu: rtx6000 (wpai vgpu 20)

框架 耗时 推理速度 加速比
funasr 368.8s 46.34 1.0
fasr 153.92s 111.03 2.4

vad

测试结果

cpu: Intel(R) Xeon(R) Silver 4210 CPU @ 2.20GHz (wpai cpu 2核)

gpu: rtx6000 (wpai vgpu 20)

框架 耗时 推理速度 加速比
funasr 219.8s 77.75 1.0
fasr 86.32s 197.98 2.55

单通道音频

pipeline

vad->asr->punc

测试结果

cpu: Intel(R) Xeon(R) Silver 4210 CPU @ 2.20GHz (wpai cpu 2核)

gpu: rtx6000 (wpai vgpu 20)

框架 耗时 推理速度 加速比
funasr 123.8s 22.05 1.0
fasr 59.04s 46.24 2.1

vad

测试结果

cpu: Intel(R) Xeon(R) Silver 4210 CPU @ 2.20GHz (wpai cpu 2核)

gpu: rtx6000 (wpai vgpu 20)

框架 耗时 推理速度 加速比
funasr 59.26s 46.07 1.0
fasr 36.84s 74.1 1.61

AISHELL

pipeline

vad->asr->punc

测试结果

cpu: Intel(R) Xeon(R) Silver 4210 CPU @ 2.20GHz (wpai cpu 2核)

gpu: rtx6000 (wpai vgpu 20)

框架 耗时 推理速度 加速比
funasr 123.8s 18.65 1.0
fasr 59.04s 32.71 1.8

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

fasr-0.1.8.tar.gz (3.3 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

fasr-0.1.8-py3-none-any.whl (3.3 MB view details)

Uploaded Python 3

File details

Details for the file fasr-0.1.8.tar.gz.

File metadata

  • Download URL: fasr-0.1.8.tar.gz
  • Upload date:
  • Size: 3.3 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.5.4

File hashes

Hashes for fasr-0.1.8.tar.gz
Algorithm Hash digest
SHA256 ea1a5d790a42170e5779c6c2d70b95f69242f5f5c727d9df8a7bbac9cb7a29c6
MD5 9bbf0ec39464bd7cd2853a6fb05cbf2c
BLAKE2b-256 cb6eb3435e90b6fc733c7ee543b191d63f17afa0c7068c272cb070e150f886a5

See more details on using hashes here.

File details

Details for the file fasr-0.1.8-py3-none-any.whl.

File metadata

  • Download URL: fasr-0.1.8-py3-none-any.whl
  • Upload date:
  • Size: 3.3 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.5.4

File hashes

Hashes for fasr-0.1.8-py3-none-any.whl
Algorithm Hash digest
SHA256 e4b6a292f08e392786508759f12d600be2f6ec5680e544b62fe78f324c382644
MD5 eb166f9fa59f5287346ce985e2d7c7fa
BLAKE2b-256 b0dd29e44c95d29520d552d7e2b7164cc1da12005025cdc2ebbebb0d0ccfcdbc

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page