[D] What's stopping you from working on speech and voice?

• Kaldi Speech Recognition Toolkit

  23 14,321 7.2 Shell

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

  

  - https://github.com/kaldi-asr/kaldi

• SaaSHub

  www.saashub.com featured

  SaaSHub - Software Alternatives and Reviews. SaaSHub helps you find the best software and product alternatives

  

• espnet

  15 8,562 9.9 Python

  End-to-End Speech Processing Toolkit

  

  - https://github.com/espnet/espnet

• speechbrain

  27 8,993 9.8 Python

  A PyTorch-based Speech Toolkit

  

  - https://github.com/speechbrain/speechbrain

• NeMo

  30 12,305 9.9 Python

  A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

  

  - https://github.com/NVIDIA/NeMo

• UniSpeech

  1 436 4.5 Python

  UniSpeech - Large Scale Self-Supervised Learning for Speech

  

  - https://github.com/microsoft/UniSpeech

• VBx

  1 256 2.9 Python

  Variational Bayes HMM over x-vectors diarization

  

  - https://github.com/BUTSpeechFIT/VBx

• thunder-speech

  1 25 0.0 Python

  A Hackable speech recognition library.

  Have you tried https://github.com/scart97/thunder-speech? It's a smaller repo that is based off of NeMo, but meant to be for more flexible experimentation, and is compatible with huggingface's transformers library.

Suggest a related project