A torch implementation of a recursion which turns out to be useful for RNN-T.
☆150Aug 25, 2023Updated 2 years ago
Alternatives and similar repositories for fast_rnnt
Users that are interested in fast_rnnt are comparing it to the libraries listed below
Sorting:
- Memory efficient transducer loss computation☆69Jun 10, 2022Updated 3 years ago
- CUDA-Warp RNN-Transducer☆216Feb 22, 2023Updated 3 years ago
- ☆67Mar 25, 2022Updated 3 years ago
- A fast parallel implementation of RNN Transducer.☆314Jun 7, 2023Updated 2 years ago
- a lightweight speech processing toolkit based on Pytorch and (Py)Kaldi☆344Dec 25, 2020Updated 5 years ago
- Torch-based tool for quantizing high-dimensional vectors using additive codebooks☆54May 25, 2022Updated 3 years ago
- An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.☆67Jan 7, 2026Updated last month
- Kaldi-compatible online & offline feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd - P…☆213Aug 7, 2025Updated 6 months ago
- E2E system with LF-MMI; word N-gram for Mandarin☆166Apr 29, 2022Updated 3 years ago
- A CRF-based ASR Toolkit☆364Feb 5, 2026Updated last month
- FSA/FST algorithms, differentiable, with PyTorch compatibility.☆1,306Nov 19, 2025Updated 3 months ago
- [ASRU 2021] Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition☆219Jun 22, 2023Updated 2 years ago
- Moved to https://github.com/k2-fsa/icefall☆146Oct 13, 2022Updated 3 years ago
- End-to-end ASR/LM implementation with PyTorch☆594Aug 30, 2021Updated 4 years ago
- PyTorch implementation of LF-MMI for End-to-end ASR☆220Jan 14, 2021Updated 5 years ago
- ☆276Jan 15, 2021Updated 5 years ago
- In this repository, I try to combine k2 with speechbrain to decode well and fastly.☆16Jun 17, 2022Updated 3 years ago
- Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva☆91Feb 18, 2025Updated last year
- 3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition☆118Jun 22, 2022Updated 3 years ago
- Python wrapper for OpenFST and its extensions from Kaldi. Also support reading/writing ark/scp files☆55Sep 1, 2025Updated 6 months ago
- A fast and lightweight python-based CTC beam search decoder for speech recognition.☆469Jul 13, 2023Updated 2 years ago
- ☆76Mar 18, 2022Updated 3 years ago
- Python wrapper for kaldi's arpa2fst☆38Aug 27, 2025Updated 6 months ago
- A Fast Sequence Transducer Implementation with PyTorch Bindings☆199Sep 20, 2022Updated 3 years ago
- Tools for handling multimodal data in machine learning projects.☆1,116Updated this week
- Python wrappers for Kaldi Levenshtein's distance and alignment code.☆68Jan 5, 2026Updated 2 months ago
- magicspeech competition recipe☆18Jun 29, 2020Updated 5 years ago
- Recurrent Neural Aligner☆51Apr 14, 2020Updated 5 years ago
- Working online speech recognition based on RNN Transducer. ( Trained model release available in release )☆292Aug 5, 2021Updated 4 years ago
- [NeurIPS'22] Squeezeformer: An Efficient Transformer for Automatic Speech Recognition☆264Feb 12, 2023Updated 3 years ago
- The RWTH ASR Toolkit.☆58Feb 27, 2026Updated last week
- streaming attention networks for end-to-end automatic speech recognition☆55May 6, 2020Updated 5 years ago
- ☆1,369Updated this week
- ☆46Nov 2, 2023Updated 2 years ago
- Segment a given audio into utterances using a trained end-to-end ASR model.☆74Oct 9, 2020Updated 5 years ago
- Large, modern dataset for speech recognition☆721Feb 26, 2024Updated 2 years ago
- Segment an audio file and obtain utterance alignments. (Python package)☆345May 15, 2024Updated last year
- Incorporating KenLM language model with HuggingFace implementation of Wav2Vec2CTC Model using beam search decoding☆75Oct 11, 2021Updated 4 years ago
- A fast parallel implementation of RNN Transducer.☆12Apr 8, 2025Updated 10 months ago