๐Ÿ† #542 overall#43 of 301 in Speech Recognition

mravanelli /pytorch-kaldi

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.

$ git clone https://github.com/mravanelli/pytorch-kaldi.git
GitHub social preview for mravanelli/pytorch-kaldi
Stars
2.4K
2,406
Forks
442
442
Language
Python
License
None
Created
Feb 27, 2018
8.6 years old
Last push
Mar 14, 2022

Categories

GitHub topics

More in Speech Recognition

Speech Recognition

alphacep/vosk-api

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

Jupyter NotebookApache-2.0updated Aug 9, 2026
GitHub โ†—โ˜… 15.1Kโ‘‚ 1.8K
Speech Recognition

kmario23/deep-learning-drizzle

Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!

๐Ÿง  Natural Language Processing
HTMLno licenseupdated Aug 22, 2026
GitHub โ†—โ˜… 12.9Kโ‘‚ 3K
Speech Recognition

speechbrain/speechbrain

A PyTorch-based Speech Toolkit

๐Ÿค– Language Models
PythonApache-2.0updated Aug 27, 2026
GitHub โ†—โ˜… 11.8Kโ‘‚ 1.7K
Speech Recognition

espnet/espnet๐Ÿ”ฅ active

End-to-End Speech Processing Toolkit

๐ŸŒ Machine Translation
PythonApache-2.0updated Sep 24, 2026
GitHub โ†—โ˜… 10Kโ‘‚ 2.4K
Speech Recognition

linto-ai/whisper-timestamped

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

PythonAGPL-3.0updated Aug 17, 2026
GitHub โ†—โ˜… 2.8Kโ‘‚ 209

Data from GitHub ยท snapshot Sep 24, 2026