gheyret / thuyg20_scripts
Script files of THUYG-20(A free Uyghur speech database Released by CSLT@Tsinghua University & Xinjiang University)
☆15Updated 5 years ago
Alternatives and similar repositories for thuyg20_scripts:
Users that are interested in thuyg20_scripts are comparing it to the libraries listed below
- Implementation of the paper "Confidence estimation for attention based sequence to sequence models for speech recognition"☆16Updated 3 years ago
- SChunk-Encoder (Transformer or Conformer) for streaming E2E ASR☆9Updated 2 years ago
- The project for speech translation☆11Updated last year
- 将normalize过的中文文本,做逆向normalize。具体功能即实现 chinese_text_normalization的逆向版本。☆13Updated 4 years ago
- This is the experimental description of MnTTS2.☆10Updated last year
- Shanghainese TTS☆23Updated last year
- End-to-End Speech Processing Toolkit☆13Updated 3 months ago
- This is the project page of our paper "MacST: Multi-Accent Speech Synthesis via Text Transliteration for Accent Conversion".☆9Updated last month
- open-source Mandarian biased word dataset☆11Updated last year
- Uyghur Single Speaker Speech Dataset. ウイグル語音声データセット☆26Updated 3 years ago
- A simple command line tool to calculate WER for ASR.☆14Updated 6 months ago
- ☆15Updated last year
- This repo related to the paper "A Framework for Phoneme-Level Pronunciation Assessment Using CTC" for INTERSPEECH2024☆20Updated 5 months ago
- ☆18Updated 7 months ago
- A semi-supervised sequence-to-sequence ASR☆10Updated 2 years ago
- Chinese polyphone disambiguation for Text-to-Speech application☆34Updated 10 months ago
- Forced alignment decoder for Whisper.☆14Updated last year
- A fast parallel PyTorch implementation of the "CIF: Continuous Integrate-and-Fire for End-to-End Speech Recognition" https://arxiv.org/ab…☆33Updated last year
- Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together☆47Updated 2 years ago
- The case study and multilingfual performance of ICASSP submission☆23Updated 2 years ago
- PyTorch implementation of "Nextformer: A ConvNeXt Augmented Conformer For End-To-End Speech Recognition"☆11Updated 2 years ago
- Speech Recognition for Uyghur using deep learning☆32Updated 3 years ago
- A fast parallel implementation of RNN Transducer.☆12Updated 2 weeks ago
- End-to-end MOdeling of ASR (Automatic Speech Recognition)☆33Updated 2 years ago
- ☆15Updated 9 months ago
- Torchaudio Forced Aligner for Mixed Chinese (Mandarin or Cantonese) and English.☆11Updated 4 months ago
- An extension of PHOIBLE that includes features for allophones.☆10Updated last year
- kaldi cnn-tdnnf baseline☆13Updated 3 years ago
- ☆25Updated 5 months ago
- [ICASSP 2022] Improving End-to-End Contextual Speech Recognition with Fine-Grained Contextual Knowledge Selection☆25Updated last year