pytorch-kaldi
by mravanelli (personal account)
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. (description from the project’s GitHub page)
Repository facts
- Stars
- 2,410
- Forks
- 442
- Open issues and pull requests
- 26
- Primary language
- Python
- License
- No license file detected
- Owner
- mravanelli · Personal account
- Created
- Feb 27, 2018
- Last push
- Mar 14, 2022
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 7,826: JordiCorbilla/stock-prediction-deep-neural-learning
Predicting stock prices using a TensorFlow LSTM (long short-term memory) neural network for times series forecasting
688 starsPythonApache-2.0Last push Oct 10, 2026
Rank 531: alphacep/vosk-api
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
15,181 starsJupyter NotebookApache-2.0Last push Oct 15, 2026
Rank 5,963: pykaldi/pykaldi
A Python wrapper for Kaldi
1,041 starsPythonApache-2.0Last push Nov 30, 2025
Rank 6,710: jtkim-kaist/VAD
Voice activity detection (VAD) toolkit including DNN, bDNN, LSTM and ACAM based VAD. We also provide our directly recorded dataset.
866 starsMATLABNo license file detectedLast push Jun 9, 2021
Rank 5,253: mravanelli/SincNet
SincNet is a neural architecture for efficiently processing raw audio samples.
1,246 starsPythonMITLast push Apr 28, 2021
Rank 5,545: lhotse-speech/lhotse
Tools for handling multimodal data in machine learning projects.
1,160 starsPythonApache-2.0Last push Oct 6, 2026