TeaPoly / CE-OptimizedLossLinks
Optimized loss based on cross-entropy (CE), like MWER (minimum WER) Loss with beam search and negative sampling strategy, Smoothed Max Pooling Loss.
☆23Updated 11 months ago
Alternatives and similar repositories for CE-OptimizedLoss
Users that are interested in CE-OptimizedLoss are comparing it to the libraries listed below
Sorting:
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆60Updated 2 years ago
- ☆32Updated 2 years ago
- The baseline system for the ICASSP2024 ICMC-ASR Challenge.☆53Updated last year
- ☆38Updated last year
- 3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition☆119Updated 3 years ago
- MagicData-RAMC Dataset and Baseline☆55Updated 3 years ago
- [ICASSP 2020] CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition (A PyTorch implementation of Continuous Integrate-and-…☆76Updated 8 months ago
- Chinese Text Normalization and Dataset☆85Updated 3 years ago
- ☆14Updated last year
- The project is associated with the recently-launched ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (M2MeT) to pro…☆128Updated 3 years ago
- A ctc decoder for both online and offline asr model☆64Updated last year
- End-to-End Keyword Spotting (E2E-KWS) using a character level LSTM☆42Updated 2 years ago
- E2E system with LF-MMI; word N-gram for Mandarin☆166Updated 3 years ago
- Memory efficient transducer loss computation☆69Updated 3 years ago
- ☆44Updated last year
- ☆32Updated 3 years ago
- [ICASSP2023] Source code, model links and open test sets for paper SeACo-Paraformer.☆34Updated last year
- Dynamic Chunk Streaming and Offline Conformer based on athena-team/Athena.☆44Updated 2 years ago
- Went online decode demo☆31Updated 4 years ago
- ☆13Updated 2 years ago
- AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data☆32Updated last year
- One command to build TLG.fst for WeNet.☆31Updated 2 years ago
- [ICASSP2021] Data preperation scripts, training pipeline and baseline experiment results for the Interspeech 2020 Accented English Speech…☆56Updated 4 years ago
- Mining effective negative training samples for keyword spotting (PyTorch)☆62Updated 5 years ago
- Code for synchronising all CHiME-5 audio signals for use in CHiME-6☆18Updated 5 years ago
- it's a train acoustics model code lib☆27Updated 5 years ago
- ☆37Updated 4 years ago
- ☆67Updated 3 years ago
- Code for reproducing experiments in "Domain-Adversarial Voice Activity Detection"☆24Updated 5 years ago
- TTS-frontend with Bert and CRF/lstm (For Tacotron)☆53Updated 5 years ago