k2-fsa / fast_rnntLinks
A torch implementation of a recursion which turns out to be useful for RNN-T.
☆141Updated last year
Alternatives and similar repositories for fast_rnnt
Users that are interested in fast_rnnt are comparing it to the libraries listed below
Sorting:
- ☆68Updated 3 years ago
- Memory efficient transducer loss computation☆68Updated 3 years ago
- ☆76Updated 3 years ago
- 3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition☆118Updated 3 years ago
- Moved to https://github.com/k2-fsa/icefall☆146Updated 2 years ago
- The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"☆38Updated 5 years ago
- Segment a given audio into utterances using a trained end-to-end ASR model.☆73Updated 4 years ago
- A pytorch wrapper for LF-MMI training and parallel training in Kaldi☆73Updated 3 years ago
- Dynamic Chunk Streaming and Offline Conformer based on athena-team/Athena.☆44Updated 2 years ago
- Recurrent Neural Aligner☆50Updated 5 years ago
- streaming attention networks for end-to-end automatic speech recognition☆55Updated 5 years ago
- Kaldi-compatible online & offline feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd - P…☆202Updated last week
- Python wrapper for kaldi's arpa2fst☆38Updated 7 months ago
- PyTorch implementation of "Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss" (ICASS…☆107Updated 3 years ago
- experiments with RETURNN☆158Updated last month
- Some fast-ish algorithms for batch text search in moderate-sized collections, intended for data cleanup☆71Updated last week
- An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.☆68Updated 4 years ago
- E2E system with LF-MMI; word N-gram for Mandarin☆165Updated 3 years ago
- PyTorch implementation of LF-MMI for End-to-end ASR☆220Updated 4 years ago
- The project is associated with the recently-launched ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (M2MeT) to pro…☆120Updated 3 years ago
- CUDA-Warp RNN-Transducer☆212Updated 2 years ago
- mWER loss implementation in tensorflow☆31Updated 4 years ago
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆58Updated last year
- Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context☆196Updated 10 months ago
- Python package for combining diarization system outputs.☆88Updated last year
- Chinese Text Normalization and Dataset☆84Updated 3 years ago
- E2E-SincNet: Toward fully end-to-end speech recognition☆30Updated 5 years ago
- A pytorch_lightning reimplementation of the Transducer module from ESPnet.☆77Updated 4 years ago
- Implementation of audio degradation processes☆103Updated 9 years ago
- Discriminative Neural Clustering for Speaker Diarisation☆78Updated 3 years ago