APAM toolkit is built on PyTorch and provides recipes to adapt pretrained acoustic models with a variety of sequence discriminative training criterions.
☆14Feb 15, 2021Updated 5 years ago
Alternatives and similar repositories for apam
Users that are interested in apam are comparing it to the libraries listed below
Sorting:
- A pytorch wrapper for LF-MMI training and parallel training in Kaldi☆73Jun 8, 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
- it's a train acoustics model code lib☆27May 20, 2020Updated 5 years ago
- ☆22Jul 8, 2019Updated 6 years ago
- ☆17Nov 25, 2019Updated 6 years ago
- Pronunciation-assisted Subword Modeling☆31May 30, 2019Updated 6 years ago
- In this repository, I try to combine k2 with speechbrain to decode well and fastly.☆16Jun 17, 2022Updated 3 years ago
- ☆16Jun 13, 2022Updated 3 years ago
- Kaldi style neural network training in pytorch for use in place of nnet3 in Kaldi.☆26Jul 25, 2024Updated last year
- pytorch CTC implementation for ASR. Use eesen's fst decoder framework☆10Feb 27, 2020Updated 6 years ago
- ☆48Jan 8, 2021Updated 5 years ago
- ☆10Sep 19, 2022Updated 3 years ago
- This is an extension of kaldi speech recognition software which allows to perform decoding of speech with hybrid word and phoneme graphs.…☆11Feb 4, 2020Updated 6 years ago
- Python wrapper for OpenFST and its extensions from Kaldi. Also support reading/writing ark/scp files☆55Sep 1, 2025Updated 6 months ago
- ☆28Oct 7, 2025Updated 4 months ago
- Efficient Neural Architecture Search via Straight-Through Gradients☆13Nov 12, 2020Updated 5 years ago
- Text normalization scripts from IRISA lab☆14Jun 1, 2018Updated 7 years ago
- Chinese-ASR built on kaldi☆14Jan 21, 2019Updated 7 years ago
- Custom decoders for Kaldi☆13Jun 5, 2019Updated 6 years ago
- Conversion of recurrent neural network language models to weighted finite state transducers☆58Jun 1, 2018Updated 7 years ago
- Script for converting kaldi GMM/HMM models to HTK format☆11Jul 18, 2024Updated last year
- Kaldi extended by Kaituo XU with new features in nnet1.☆12Dec 16, 2018Updated 7 years ago
- ASR library☆14Dec 3, 2018Updated 7 years ago
- it's ASR decoder and make graph project☆33May 26, 2022Updated 3 years ago
- PyTorch implementation of LF-MMI for End-to-end ASR☆220Jan 14, 2021Updated 5 years ago
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆59Sep 6, 2023Updated 2 years ago
- Code for ACL-IJCNLP 2021 paper "N-Best-ASR-Transformer: Enhancing SLU Performance using Multiple ASR Hypotheses."☆17Nov 30, 2021Updated 4 years ago
- Properly handle position-dependent phones in a subword lexicon FST☆31Oct 26, 2020Updated 5 years ago
- A set of scripts to use in preparing a corpus for speech-to-text processing with the Kaldi Automatic Speech Recognition Library.☆15May 19, 2020Updated 5 years ago
- Source code for ACL 2020 paper "Learning Spoken Language Representations with Neural Lattice Language Modeling"☆17Feb 11, 2023Updated 3 years ago
- A python package that make tensorflow be able to read "Kaldi" scp/ark in an elegant way. May kaldi user happy to enter tensorflow world.☆40Nov 26, 2018Updated 7 years ago
- The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"☆39Jun 9, 2020Updated 5 years ago
- Vector Quantized Autoregressive Predictive Coding (VQ-APC)☆37Nov 11, 2020Updated 5 years ago
- Mispronunciation detection code for jingju singing voice☆20Sep 5, 2018Updated 7 years ago
- A Python interface to OpenFst (fix FstDrawer interface issue for 1.6 version)☆17Apr 2, 2018Updated 7 years ago
- ☆40Aug 15, 2021Updated 4 years ago
- ☆41Jun 25, 2018Updated 7 years ago
- Multilingual and code-switching ASR challenges for low resource Indian languages.☆21Jul 26, 2021Updated 4 years ago
- Segment a given audio into utterances using a trained end-to-end ASR model.☆74Oct 9, 2020Updated 5 years ago