tencent-ailab / 3m-asrLinks
3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition
☆119Updated 3 years ago
Alternatives and similar repositories for 3m-asr
Users that are interested in 3m-asr are comparing it to the libraries listed below
Sorting:
- A torch implementation of a recursion which turns out to be useful for RNN-T.☆143Updated last year
- E2E system with LF-MMI; word N-gram for Mandarin☆166Updated 3 years ago
- Dynamic Chunk Streaming and Offline Conformer based on athena-team/Athena.☆44Updated 2 years ago
- Memory efficient transducer loss computation☆68Updated 3 years ago
- ☆68Updated 3 years ago
- Chinese Text Normalization and Dataset☆84Updated 3 years ago
- PyTorch implementation of "Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss" (ICASS…☆108Updated 3 years ago
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆58Updated last year
- A pytorch_lightning reimplementation of the Transducer module from ESPnet.☆77Updated 4 years ago
- The project is associated with the recently-launched ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (M2MeT) to pro…☆123Updated 3 years ago
- ☆76Updated 3 years ago
- A ctc decoder for both online and offline asr model☆64Updated last year
- The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"☆38Updated 5 years ago
- mWER loss implementation in tensorflow☆31Updated 4 years ago
- streaming attention networks for end-to-end automatic speech recognition☆55Updated 5 years ago
- ☆61Updated 2 years ago
- [ICASSP2021] Data preperation scripts, training pipeline and baseline experiment results for the Interspeech 2020 Accented English Speech…☆55Updated 4 years ago
- Optimized loss based on cross-entropy (CE), like MWER (minimum WER) Loss with beam search and negative sampling strategy, Smoothed Max Po…☆22Updated 9 months ago
- Segment a given audio into utterances using a trained end-to-end ASR model.☆73Updated 4 years ago
- Recurrent Neural Aligner☆50Updated 5 years ago
- ☆44Updated 4 years ago
- Kaldi-compatible online & offline feature extraction with PyTorch, supporting CUDA, batch processing, chunk processing, and autograd - P…☆203Updated last month
- [ICASSP 2020] CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition (A PyTorch implementation of Continuous Integrate-and-…☆73Updated 7 months ago
- A pytorch wrapper for LF-MMI training and parallel training in Kaldi☆73Updated 3 years ago
- Moved to https://github.com/k2-fsa/icefall☆146Updated 2 years ago
- A Full Text-Dependent End to End Mispronunciation Detection and Diagnosis with Easy Data Augment Techniques☆61Updated 4 years ago
- ☆128Updated 4 years ago
- Python wrapper for kaldi's arpa2fst☆38Updated 8 months ago
- An effort to track benchmarking results over widely-used datasets for ASR.☆47Updated 3 years ago
- An open-source implementation of sequence-to-sequence based speech processing engine☆38Updated 2 years ago