csukuangfj / optimized_transducerLinks
Memory efficient transducer loss computation
☆68Updated 3 years ago
Alternatives and similar repositories for optimized_transducer
Users that are interested in optimized_transducer are comparing it to the libraries listed below
Sorting:
- ☆68Updated 3 years ago
- ☆76Updated 3 years ago
- A torch implementation of a recursion which turns out to be useful for RNN-T.☆142Updated last year
- Recurrent Neural Aligner☆50Updated 5 years ago
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆58Updated last year
- The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"☆38Updated 5 years ago
- Dynamic Chunk Streaming and Offline Conformer based on athena-team/Athena.☆44Updated 2 years ago
- streaming attention networks for end-to-end automatic speech recognition☆55Updated 5 years ago
- Python wrapper for kaldi's arpa2fst☆38Updated 7 months ago
- mWER loss implementation in tensorflow☆31Updated 4 years ago
- An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.☆68Updated 4 years ago
- A pytorch wrapper for LF-MMI training and parallel training in Kaldi☆73Updated 3 years ago
- 3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition☆118Updated 3 years ago
- Pronunciation-assisted Subword Modeling☆30Updated 6 years ago
- Segment a given audio into utterances using a trained end-to-end ASR model.☆73Updated 4 years ago
- ☆48Updated 4 years ago
- ☆61Updated 2 years ago
- ☆44Updated last year
- python wrapper for kaldi's native I/O☆27Updated 6 months ago
- Code for reproducing experiments in "Domain-Adversarial Voice Activity Detection"☆23Updated 5 years ago
- A pytorch_lightning reimplementation of the Transducer module from ESPnet.☆77Updated 4 years ago
- it's a train acoustics model code lib☆27Updated 5 years ago
- Multistream CNN for Robust Acoustic Modeling☆40Updated 4 years ago
- Some fast-ish algorithms for batch text search in moderate-sized collections, intended for data cleanup☆72Updated last month
- python codes to extract MFCC and FBANK speech features for Kaldi☆66Updated 6 years ago
- Python wrapper for OpenFST and its extensions from Kaldi. Also support reading/writing ark/scp files☆53Updated 3 months ago
- Optimized loss based on cross-entropy (CE), like MWER (minimum WER) Loss with beam search and negative sampling strategy, Smoothed Max Po…☆22Updated 9 months ago
- use 3 chinese senteces as training corpus to show how to build lm model and HCLG decoding graph☆8Updated 5 years ago
- Python wrappers for Kaldi Levenshtein's distance and alignment code.☆67Updated 2 months ago
- ☆32Updated 2 years ago