🏆 #2,291 overall#289 of 795 in Speech Recognition

chenkui164 /FastASR

这是一个用C++实现ASR推理的项目,它依赖很少,安装也很简单,推理速度很快,在树莓派4B等ARM平台也可以流畅的运行。 支持的模型是由Google的Transformer模型中优化而来,数据集是开源wenetspeech(10000+小时)或阿里私有数据集(60000+小时), 所以识别效果也很好,可以媲美许多商用的ASR软件。

$ git clone https://github.com/chenkui164/FastASR.git
GitHub social preview for chenkui164/FastASR
Stars
554
554
This week
0 ★
Forks
79
79
Language
C
License
Apache-2.0
Created
Jul 8, 2022
4.4 years old
Last push
Mar 19, 2023

Stars, last 17 days

Oct 28, 2026 → Nov 16, 2026
★ 554▲ +0★ 554

Categories

GitHub topics

More in Speech Recognition

Speech Recognition

ggml-org/whisper.cpp🔥 active

▲ +231 ★ this week

Port of OpenAI's Whisper model in C/C++

C++MITupdated Nov 16, 2026
GitHub ↗★ 55.2K⑂ 6.3K
Speech Recognition

SYSTRAN/faster-whisper🔥 active

▲ +213 ★ this week

Faster Whisper transcription with CTranslate2

PythonMITupdated Nov 12, 2026
GitHub ↗★ 26.8K⑂ 2.3K
Speech Recognition

m-bain/whisperX🔥 active

▲ +228 ★ this week

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

PythonBSD-2-Clauseupdated Nov 12, 2026
GitHub ↗★ 25.4K⑂ 2.6K
Speech Recognition

kaldi-asr/kaldi

▲ +4 ★ this week

kaldi-asr/kaldi is the official location of the Kaldi project.

ShellOtherupdated Sep 22, 2025
GitHub ↗★ 15.5K⑂ 5.3K
Speech Recognition

abus-aikorea/voice-pro

▲ +20 ★ this week

Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.

PythonGPL-3.0updated Jul 13, 2026
GitHub ↗★ 13.4K⑂ 1.9K
Speech Recognition

PaddlePaddle/PaddleSpeech

▲ +7 ★ this week

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

PythonApache-2.0updated Aug 12, 2026
GitHub ↗★ 12.7K⑂ 2K

Data from GitHub · snapshot Nov 16, 2026