Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.
☆59Sep 6, 2023Updated 2 years ago
Alternatives and similar repositories for CTC-OptimizedLoss
Users that are interested in CTC-OptimizedLoss are comparing it to the libraries listed below
Sorting:
- mWER loss implementation in tensorflow☆31Sep 7, 2020Updated 5 years ago
- Optimized loss based on cross-entropy (CE), like MWER (minimum WER) Loss with beam search and negative sampling strategy, Smoothed Max Po…☆24Oct 11, 2024Updated last year
- E2E system with LF-MMI; word N-gram for Mandarin☆167Apr 29, 2022Updated 3 years ago
- An extension of thu-spmi/CAT which contains a full-fledged implementation of CTC-CRF for Tensorflow.☆12Jul 5, 2021Updated 4 years ago
- Efficient Neural Architecture Search via Straight-Through Gradients☆13Nov 12, 2020Updated 5 years ago
- it's a train acoustics model code lib☆27May 20, 2020Updated 5 years ago
- End-to-End Speech Processing Toolkit☆15Jan 20, 2025Updated last year
- Segment a given audio into utterances using a trained end-to-end ASR model.☆74Oct 9, 2020Updated 5 years ago
- ☆16Jun 13, 2022Updated 3 years ago
- A Python interface to OpenFst (fix FstDrawer interface issue for 1.6 version)☆17Apr 2, 2018Updated 7 years ago
- A torch implementation of a recursion which turns out to be useful for RNN-T.☆149Aug 25, 2023Updated 2 years ago
- APAM toolkit is built on PyTorch and provides recipes to adapt pretrained acoustic models with a variety of sequence discriminative train…☆14Feb 15, 2021Updated 5 years ago
- ☆15Nov 5, 2021Updated 4 years ago
- 3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition☆118Jun 22, 2022Updated 3 years ago
- a lightweight speech processing toolkit based on Pytorch and (Py)Kaldi☆344Dec 25, 2020Updated 5 years ago
- Implements of CTC, Speech-Transformer and CIF for end-to-end speech recognition with pytorch☆23Jul 28, 2020Updated 5 years ago
- ☆76Mar 18, 2022Updated 4 years ago
- it's ASR decoder and make graph project☆33May 26, 2022Updated 3 years ago
- Towards hot directions in industrial end to end speech recognition☆331Nov 30, 2021Updated 4 years ago
- ☆40Aug 15, 2021Updated 4 years ago
- WarpRNNT loss ported in Numba CPU/CUDA for Pytorch☆17Mar 11, 2022Updated 4 years ago
- A CRF-based ASR Toolkit☆366Feb 5, 2026Updated last month
- PyTorch Implementations for End-to-End Automatic Speech Recognition☆127Jun 10, 2019Updated 6 years ago
- ☆37Jun 28, 2021Updated 4 years ago
- ☆277Jan 15, 2021Updated 5 years ago
- Memory efficient transducer loss computation☆70Jun 10, 2022Updated 3 years ago
- [ASRU 2021] Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition☆219Jun 22, 2023Updated 2 years ago
- A No-Recurrence Sequence-to-Sequence Model for Speech Recognition☆379Jul 21, 2022Updated 3 years ago
- CUDA-Warp RNN-Transducer☆216Feb 22, 2023Updated 3 years ago
- Python implementation of CTC beam search decoder + agnostic LM scorer☆20Dec 16, 2020Updated 5 years ago
- magicspeech competition recipe☆18Jun 29, 2020Updated 5 years ago
- [ICASSP 2020] CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition (A PyTorch implementation of Continuous Integrate-and-…☆80Jan 9, 2025Updated last year
- The project for speech translation☆12Sep 28, 2023Updated 2 years ago
- Primer on CTC implementation in pure Python PyTorch code☆112Jul 27, 2024Updated last year
- Custom decoders for Kaldi☆13Jun 5, 2019Updated 6 years ago
- ☆33Aug 6, 2021Updated 4 years ago
- [ICASSP2023] Source code, model links and open test sets for paper SeACo-Paraformer.☆44Mar 15, 2024Updated 2 years ago
- Implementation of CTC alignment-based single step non-autoregressive transformer☆13Jun 2, 2023Updated 2 years ago
- Multilingual and code-switching ASR challenges for low resource Indian languages.☆21Jul 26, 2021Updated 4 years ago