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(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
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
fasr-0.1.4.tar.gz
(38.6 kB
view details)
Built Distribution
fasr-0.1.4-py3-none-any.whl
(47.5 kB
view details)
File details
Details for the file fasr-0.1.4.tar.gz
.
File metadata
- Download URL: fasr-0.1.4.tar.gz
- Upload date:
- Size: 38.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.8.3 CPython/3.12.2 Darwin/22.6.0
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | b7e91cebf15179594fea7eb375af13cae98540fec6b5c603d734ff92cacec238 |
|
MD5 | 87f100f7204988973231334edf461942 |
|
BLAKE2b-256 | b5fce188ba72d0234f10d4ed085f2310e31f645f23738648a80bc717c4b93eff |
File details
Details for the file fasr-0.1.4-py3-none-any.whl
.
File metadata
- Download URL: fasr-0.1.4-py3-none-any.whl
- Upload date:
- Size: 47.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.8.3 CPython/3.12.2 Darwin/22.6.0
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 659fcf78ae515790194bb01bde80db36c61e4acb5758cff8852e2e8f9f9b3e04 |
|
MD5 | f8db97ad3511e9da149f74e8aabe6f4d |
|
BLAKE2b-256 | 99c943bc2582ad54cdf12f8b36c11c7b8645f1c996e169d4c31d2359dc4619e9 |