Yanked
This release has been yanked by its maintainers, and will be ignored by installers, except when explicitly specified.
Consider using release 0.5.0 instead.
Reason given by maintainers: this version update the model but the result is not good for some situation
audiosub
一个基于 SenseVoice 的命令行工具,用于将音频文件转换为字幕文件。
特点
- 全平台:macOS / Linux / Windows,CPU 即可跑(无需 Apple Silicon)
- 速度极快:SenseVoice int8 + silero-vad,M4 上 5 分钟音频约 5 秒
- 中文准确度高:中文识别明显优于 Whisper turbo,自带标点+ITN
- 标点即断句:按标点自动拆成短字幕,标点丢弃,无标点超 18 字/4 秒硬拆兜底
- 一键生成:简单命令即可生成 .srt 字幕文件
系统要求
- Python 3.12+
- ffmpeg(
brew install ffmpeg) - uv
使用方法
通过 uv 的 uvx 命令安装并使用。
uvx audiosub <filename>
# 将在当前目录生成 audio.srt 字幕文件
注意事项
- 支持的音频格式:MP3、WAV、M4A 等(经 ffmpeg 解码)
- 首次运行会自动下载 SenseVoice int8 + VAD 模型(约 250MB)到
~/.cache/audiosub/,请确保网络连接正常 - SenseVoice-Small 对中英混排的技术词汇(如 SQLite、Postgres 等)识别较弱;若主要处理此类内容且使用 Apple Silicon,可回退 0.3.x(mlx-whisper 版)
依赖
- Python 3.12+
- sherpa-onnx
- onnxruntime
- numpy
许可证
MIT
Metadata
Release files for audiosub 0.4.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| audiosub-0.4.0.tar.gz | 20.4 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| audiosub-0.4.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 27.1 kB
Release files / audiosub-0.4.0.tar.gz
| Download URL | audiosub-0.4.0.tar.gz |
|---|---|
| Size | 20.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e1e99055a3db11777f608a6461c93c736cc6e7b895fc784f0da81aaae8ebba34
|
|
BLAKE2b-256 checksum How to use checksums |
fc9bbf3c636f6f99f6275f7f7b586e945d5c022af81ad697dc63204d50c73956
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.12.17 {"installer":{"name":"uv","version":"0.12.17","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / audiosub-0.4.0-py3-none-any.whl
| Download URL | audiosub-0.4.0-py3-none-any.whl |
|---|---|
| Size | 6.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f647a0b688f768a38b15c893860cec266cb3414ecc0cec06e25fd9fdd347f8a0
|
|
BLAKE2b-256 checksum How to use checksums |
7f31405a92a5963bfcba772d33f8964db9ec242bb4a8cfb654b169978df14fff
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.12.17 {"installer":{"name":"uv","version":"0.12.17","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|