E2E system with LF-MMI; word N-gram for Mandarin
☆167Apr 29, 2022Updated 4 years ago
Alternatives and similar repositories for e2e_lfmmi
Users that are interested in e2e_lfmmi are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition☆120Jun 22, 2022Updated 4 years ago
- ☆34Oct 28, 2022Updated 4 years ago
- A ctc decoder for both online and offline asr model☆66Nov 18, 2023Updated 2 years ago
- A torch implementation of a recursion which turns out to be useful for RNN-T.☆148Aug 25, 2023Updated 3 years ago
- CAT is more than a CRF-based ASR toolkit: it provides a complete workflow for data-efficient end-to-end ASR, supporting CTC, CTC-CRF, RNN…☆369Feb 5, 2026Updated 9 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆277Jan 15, 2021Updated 5 years ago
- a lightweight speech processing toolkit based on Pytorch and (Py)Kaldi☆354Dec 25, 2020Updated 5 years ago
- PyTorch implementation of LF-MMI for End-to-end ASR☆221Jan 14, 2021Updated 5 years ago
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆60Sep 6, 2023Updated 3 years ago
- End-to-end ASR/LM implementation with PyTorch☆595Aug 30, 2021Updated 5 years ago
- CUDA-Warp RNN-Transducer☆215Feb 22, 2023Updated 3 years ago
- Memory efficient transducer loss computation☆71Jun 10, 2022Updated 4 years ago
- Pronunciation lexicon covering both English and Chinese languages for Automatic Speech Recognition.☆261Oct 11, 2019Updated 7 years ago
- FSA/FST algorithms, differentiable, with PyTorch compatibility.☆1,370Jul 11, 2026Updated 3 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Towards hot directions in industrial end to end speech recognition☆328Nov 30, 2021Updated 4 years ago
- Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva☆93Feb 18, 2025Updated last year
- An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.☆67Jan 7, 2026Updated 9 months ago
- ☆67Mar 25, 2022Updated 4 years ago
- it's a train acoustics model code lib☆27May 20, 2020Updated 6 years ago
- Kaldi-compatible online & offline feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd - P…☆218Jul 10, 2026Updated 3 months ago
- ☆24Mar 13, 2020Updated 6 years ago
- Large, modern dataset for speech recognition☆734Feb 26, 2024Updated 2 years ago
- A fast parallel implementation of RNN Transducer.☆315Jun 7, 2023Updated 3 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- kaldi cnn-tdnnf baseline☆13Aug 31, 2021Updated 5 years ago
- [ASRU 2021] Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition☆219Jun 22, 2023Updated 3 years ago
- ☆16Jun 13, 2022Updated 4 years ago
- Moved to https://github.com/k2-fsa/icefall☆146Oct 13, 2022Updated 4 years ago
- SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.☆558Mar 29, 2025Updated last year
- mWER loss implementation in tensorflow☆31Sep 7, 2020Updated 6 years ago
- Minimize kaldi nnet3 chain decoder☆45Jan 10, 2020Updated 6 years ago
- Decoders from Kaldi using OpenFst☆36Oct 21, 2026Updated 2 weeks ago
- Production first, nn-based on-device signal processing toolkit.☆63May 30, 2023Updated 3 years ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- magicspeech competition recipe☆18Jun 29, 2020Updated 6 years ago
- Chinese text normalization for speech processing☆744Mar 18, 2023Updated 3 years ago
- A No-Recurrence Sequence-to-Sequence Model for Speech Recognition☆378Jul 21, 2022Updated 4 years ago
- Torch-based tool for quantizing high-dimensional vectors using additive codebooks☆54May 25, 2022Updated 4 years ago
- ☆1,522Oct 28, 2026Updated last week
- Tools for Speech Enhancement integrated with Kaldi☆434Jul 6, 2023Updated 3 years ago
- Tools for handling multimodal data in machine learning projects.☆1,161Updated this week