#1515th of 38 in VoiceFor voice, speech and music
speechbrain
PyTorch toolkit for training and running speech and text models
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 11.9k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
11,331 on 31 Mar 202611,894 on 20 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
SpeechBrain is a PyTorch toolkit with over 200 training recipes on more than 40 datasets, covering ASR, speaker recognition, speech separation and enhancement, TTS, vocoding, diarization and EEG classification. Training is driven by a Python script plus a YAML hyperparameter file, and over 100 pretrained models on HuggingFace load through a short inference API. It targets research and prototyping rather than turnkey deployment.
Who it is for: Speech researchers and engineers training or fine-tuning audio models
Strengths
- Over 200 recipes on 40+ datasets, with a consistent layout across tasks
- Over 100 pretrained models on HuggingFace; ASR inference in three lines of Python
- Single and multi-GPU training, dynamic batching and mixed precision built in
- Over 30 tutorials; Apache-2.0 license permits commercial use
Weaknesses
- Library and research toolkit, not a ready-to-run server or app
- No Docker image or HTTP API provided
- Hardware requirements for training recipes are not stated
- Real-time and streaming support is listed only as a future plan
What it needs
- GPU optional
- Needs PyTorch, HuggingFace
- Models: Whisper, Wav2Vec2, WavLM, Hubert, GPT2
Also in Voice
See all 38| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing and dictation with local speech models | 83 out of 100 |
| 2 | whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription | 77 out of 100 |
| 3 | VoiceboxLocal voice studio for cloning, TTS, dictation and agent speech | 71 out of 100 |
| #4 | buzzOffline desktop app for transcribing and translating audio with Whisper | 69 out of 100 |
| #5 | meetilyDesktop app that records, transcribes and summarizes meetings locally | 68 out of 100 |