Mddct / WeUSM
☆13Updated last year
Related projects ⓘ
Alternatives and complementary repositories for WeUSM
- Optimized loss based on cross-entropy (CE), like MWER (minimum WER) Loss with beam search and negative sampling strategy, Smoothed Max Po…☆20Updated 3 weeks ago
- One command to build TLG.fst for WeNet.☆29Updated 2 years ago
- it's ASR decoder and make graph project☆32Updated 2 years ago
- Chinese Text Normalization and Dataset☆81Updated 2 years ago
- ☆31Updated 2 years ago
- AutoPrep: An Automatic Preprocessing Framework for In-the-Wild Speech Data☆29Updated 10 months ago
- MagicData-RAMC Dataset and Baseline☆49Updated 2 years ago
- TTS-frontend with Bert and CRF/lstm (For Tacotron)☆49Updated 4 years ago
- Production first, nn-based on-device signal processing toolkit.☆64Updated last year
- End-to-End Keyword Spotting (E2E-KWS) using a character level LSTM☆38Updated last year
- Python wrapper for kaldi's arpa2fst☆38Updated last year
- [ICASSP2023] Source code, model links and open test sets for paper SeACo-Paraformer.☆25Updated 7 months ago
- ☆31Updated 3 years ago
- A ctc decoder for both online and offline asr model☆58Updated 11 months ago
- The baseline system for the ICASSP2024 ICMC-ASR Challenge.☆45Updated 11 months ago
- Predict prosody labels for Chinese sentences.☆40Updated 2 years ago
- The project is associated with the recently-launched ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge (M2MeT) to pro…☆113Updated 2 years ago
- ☆35Updated 3 months ago
- ☆75Updated 2 years ago
- SLT 2024 Challenge: Post-ASR-Speaker-Tagging☆14Updated 4 months ago
- ☆61Updated last year
- Python wrapper for OpenFST and its extensions from Kaldi. Also support reading/writing ark/scp files☆46Updated 4 months ago
- ☆119Updated 3 years ago
- Memory efficient transducer loss computation☆68Updated 2 years ago
- Chinese Prosodic Structure Prediction☆10Updated 5 years ago
- Implementation of CTC alignment-based single step non-autoregressive transformer☆12Updated last year
- This repository contains a set of codes to run (i.e., train, perform inference with, evaluate) a diarization method called EEND-vector-cl…☆70Updated 2 years ago
- ☆74Updated 2 years ago
- ☆43Updated 3 years ago