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.
☆2,385Updated 3 years ago
Alternatives and similar repositories for pytorch-kaldi:
Users that are interested in pytorch-kaldi are comparing it to the libraries listed below
- Speech Recognition using DeepSpeech2.☆2,114Updated 2 years ago
- A Python wrapper for Kaldi☆1,014Updated 3 months ago
- This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pyt…☆1,198Updated 4 years ago
- A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.☆787Updated 2 years ago
- A PyTorch Implementation of End-to-End Models for Speech-to-Text☆758Updated last year
- Toolkit for efficient experimentation with Speech Recognition, Text2Speech and NLP☆1,559Updated 3 years ago
- This is the library for the Unbounded Interleaved-State Recurrent Neural Network (UIS-RNN) algorithm, corresponding to the paper Fully Su…☆1,571Updated 7 months ago
- SincNet is a neural architecture for efficiently processing raw audio samples.☆1,169Updated 3 years ago
- End-to-end ASR/LM implementation with PyTorch