hfutami / distill-bert-for-seq2seq-asr
☆24Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for distill-bert-for-seq2seq-asr
- Token-Level Supervised Contrastive Learning for Punctuation Restoration☆29Updated 3 years ago
- ☆16Updated 2 years ago
- End-to-end Speech Translation☆36Updated 3 years ago
- unsupervised ASR (mainly phone classifier) using EODM and GAN☆12Updated 4 years ago
- Pronunciation-assisted Subword Modeling☆29Updated 5 years ago
- This repository is for the paper Incorporating External POS Tagger for Punctuation Restoration. Proc. Interspeech 2021, 1987-1991, doi: 1…☆11Updated last year
- The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"☆37Updated 4 years ago
- ☆20Updated 3 years ago
- ☆36Updated 2 years ago
- [ICASSP 2022] Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection☆25Updated last year
- ASCEND Chinese-English code-switching dataset☆22Updated 2 years ago
- CMU multilingual speech repository☆31Updated 2 years ago
- Implementation of CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning☆46Updated last year
- A fast parallel PyTorch implementation of the "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition" https://arxiv.org/ab…☆32Updated 9 months ago
- Dynamic Chunk Streaming and Offline Conformer based on athena-team/Athena.☆43Updated 2 years ago
- End-to-End Speech Processing Toolkit☆11Updated this week
- Learning ASR-Robust Contextualized Embeddings for Spoken Language Understanding☆24Updated last year
- Semi-supervised spoken language understanding (SLU) via self-supervised speech and language model pretraining☆12Updated 3 years ago
- Unsupervised spoken sentence embeddings☆14Updated last year
- HMM, CTC, RNN-Transducer, forward-backward algorithm☆19Updated last year
- Making Espnet easier to use☆52Updated 3 years ago
- The project for speech translation☆11Updated last year
- Meta-learning model agnostic (MAML) implementation for cross-accented ASR☆44Updated 9 months ago
- A fast parallel implementation of RNN Transducer.☆11Updated last year
- The case study and multilingfual performance of ICASSP submission☆19Updated 2 years ago
- Implementation of the contextual biasing for ASR decoding on GPUs without lattice generation. The code supports submission to Interspeech…☆19Updated last year
- LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models☆22Updated 3 months ago
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆57Updated last year