Losses and decoders for end-to-end ASR and OCR
☆34Oct 30, 2020Updated 5 years ago
Alternatives and similar repositories for end2end
Users that are interested in end2end are comparing it to the libraries listed below
Sorting:
- Lattice combination algorithm to combine inaccurate transcripts with hypothesis lattices☆16Mar 19, 2024Updated 2 years ago
- PyTorch speech2text inference script for the NVidia openseq2seq wav2letter model variant☆10Aug 12, 2019Updated 6 years ago
- STT Service based on Kaldi ASR☆15Aug 17, 2018Updated 7 years ago
- ☆26Apr 21, 2021Updated 4 years ago
- ☆10Nov 1, 2025Updated 4 months ago
- Perform the forced decoding with target transcription☆11Sep 12, 2018Updated 7 years ago
- A PyTorch implementation of a punctuation prediction system using (B)LSTM, which automatically adds suitable punctuation into text withou…☆63May 13, 2020Updated 5 years ago
- Enable RNNLM lattice rescoring with Pytorch [kaldi]☆12Jun 5, 2020Updated 5 years ago
- A Fast Sequence Transducer Implementation with PyTorch Bindings☆200Sep 20, 2022Updated 3 years ago
- ESPnet extensions for semi-supervised end-to-end speech recognition. See also https://github.com/ShigekiKarita/espnet-semi-supervised/tre…☆38Feb 13, 2020Updated 6 years ago
- This repository contains the files used for our Interspeech 2017 paper.☆16May 30, 2017Updated 8 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
- Adapt Kaldi-ASR nnet3 chain models from Zamia-Speech.org to a different language model☆33Jan 26, 2020Updated 6 years ago
- Implementation of different noise embeddings for noise aware training of Kaldi acoustic models.☆13Feb 13, 2021Updated 5 years ago
- wake word spotting with kaldi☆19Dec 3, 2020Updated 5 years ago
- HMM, CTC, RNN-Transducer, forward-backward algorithm☆20Sep 5, 2023Updated 2 years ago
- Automatically constructing corpus for automatic speech recognition from YouTube videos☆157Feb 15, 2020Updated 6 years ago
- CTC+Beam_Search+kenlm 是用于以汉字为声学模型建模单元的解码系统☆48Jun 27, 2018Updated 7 years ago
- PyTorch implementation of LF-MMI for End-to-end ASR☆221Jan 14, 2021Updated 5 years ago
- Implementation of the contextual biasing for ASR decoding on GPUs without lattice generation. The code supports submission to Interspeech…☆21Sep 25, 2023Updated 2 years ago
- Python API for reading and querying ARPA formatted language models.☆33Sep 9, 2014Updated 11 years ago
- Custom decoders for Kaldi☆80Jun 10, 2019Updated 6 years ago
- ChiNese Text Normalization (CNTN) tool for Text-to-speech system☆37Apr 12, 2018Updated 7 years ago
- Server framework for Kaldi ASR Toolkit☆98Sep 17, 2023Updated 2 years ago
- Open Source WFST-based Decoder Toolkit☆77Feb 11, 2016Updated 10 years ago
- A torch implementation of a recursion which turns out to be useful for RNN-T.☆149Aug 25, 2023Updated 2 years ago
- Yet another speech toolkit based on Kaldi and PyTorch☆173Jul 1, 2020Updated 5 years ago
- ☆17Nov 25, 2019Updated 6 years ago
- Download and preperation tool for free speech corpora.☆16Apr 28, 2019Updated 6 years ago
- Kaldi extended by Kaituo XU with new features in nnet1.☆12Dec 16, 2018Updated 7 years ago
- 📖 LanMIT: A Toolkit for Improving Language Models in Low-resourced Speech Recognition based on Kaldi.☆22Jul 12, 2019Updated 6 years ago
- Automatically exported from code.google.com/p/transducersaurus☆11Apr 1, 2015Updated 10 years ago
- Google's TPGST reimplementation.☆34Dec 11, 2019Updated 6 years ago
- Conversion of recurrent neural network language models to weighted finite state transducers☆58Jun 1, 2018Updated 7 years ago
- Decoders from Kaldi using OpenFst☆34Jan 29, 2026Updated last month
- PyTorch code for end-to-end spoken language understanding (SLU) with ASR-based transfer learning☆231Mar 23, 2021Updated 4 years ago
- Text-Dependent Speaker Recognition System with Machine Learning Techniques☆10Dec 31, 2017Updated 8 years ago
- ICASSP 2020 ESPnet-TTS: Merlin baseline system☆36Oct 28, 2019Updated 6 years ago
- A "Crowd-Built" continuously growing speech dataset with transcripts. The dataset contains multiple languages and is intended for anyone …☆43Aug 3, 2022Updated 3 years ago