titu1994 / warprnnt_numbaLinks
WarpRNNT loss ported in Numba CPU/CUDA for Pytorch
☆17Updated 3 years ago
Alternatives and similar repositories for warprnnt_numba
Users that are interested in warprnnt_numba are comparing it to the libraries listed below
Sorting:
- ☆16Updated 3 years ago
- Memory efficient transducer loss computation☆68Updated 3 years ago
- A collection of papers related to speech model compression☆26Updated last year
- Python wrapper for kaldi's arpa2fst☆38Updated 6 months ago
- A handy dataset of noises for ASR☆21Updated 6 years ago
- CMU multilingual speech repository☆31Updated 3 years ago
- python wrapper for kaldi's native I/O☆27Updated 5 months ago
- Python wrappers for Kaldi Levenshtein's distance and alignment code.☆67Updated last month
- Multistream CNN for Robust Acoustic Modeling☆40Updated 4 years ago
- A SPMI Lab toolkit for language models.☆11Updated 8 years ago
- Lattice combination algorithm to combine inaccurate transcripts with hypothesis lattices☆16Updated last year
- Decoders from Kaldi using OpenFst☆29Updated 5 months ago
- ☆44Updated last year
- Pronunciation-assisted Subword Modeling☆29Updated 6 years ago
- ☆28Updated 4 months ago
- A fast parallel implementation of RNN Transducer.☆12Updated 2 months ago
- Torch-based tool for quantizing high-dimensional vectors using additive codebooks☆54Updated 3 years ago
- Multipurpose Multi Speaker Mixture Signal Generator☆44Updated 4 months ago
- Kaldi style neural network training in pytorch for use in place of nnet3 in Kaldi.☆26Updated 11 months ago
- ☆68Updated 3 years ago
- ☆37Updated last month
- ☆25Updated 7 months ago
- Code for the paper: How Much Context Does My Attention-Based ASR System Need?☆10Updated last month
- This repository contains the Kaldi LF-MMI implementation of the paper "Bayesian Learning of LF-MMI Trained Time Delay Neural Networks for…☆9Updated 3 years ago
- [ICLR 2022] "Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable", by Shaojin Ding, Tianlong Chen, Z…☆31Updated 3 years ago
- ☆38Updated 3 years ago
- ☆76Updated 3 years ago
- Temporary anonymous version☆22Updated last year
- Data and code related to the ICASSP submission "A comparison of methods for OOV-word recognition"☆17Updated 3 years ago
- Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva☆91Updated 4 months ago