meganndare / cantonese-nlpLinks
cantonese-mandarin unsupervised neural translation for sw project
☆27Updated 2 years ago
Alternatives and similar repositories for cantonese-nlp
Users that are interested in cantonese-nlp are comparing it to the libraries listed below
Sorting:
- Transformers for Cantonese☆57Updated 4 years ago
- Python scripts and datasets of the "Extremely Low-Resource Neural Machine Translation: A Case Study of Cantonese" project☆15Updated 2 years ago
- one script for xls-r/xlsr/whisper fine-tuning☆42Updated 2 years ago
- An audio and transcribed corpus of contemporary Hong Kong Cantonese☆38Updated 4 years ago
- An English-to-Cantonese machine translation model☆52Updated 5 months ago
- Fine-tuning Wav2Vec2.0 on Common Voice(zh-HK)☆15Updated 3 years ago
- BERT Tokenizer with vocabulary tailored for Cantonese☆22Updated 2 years ago
- Unsupervised spoken sentence embeddings☆14Updated 2 years ago
- This is a repository dedicated for pre-trained acoustic models of Hong Kong Cantonese and Cantonese forced alignment.☆16Updated 9 months ago
- The case study and multilingfual performance of ICASSP submission☆24Updated 2 years ago
- ASR text preprocessing utility☆21Updated last year
- ☆40Updated last year
- Code and pretrained models for "DUB: Discrete Unit Back-translation for Speech Translation" (ACL 2023 Findings)☆28Updated 2 years ago
- flow mirror models from JZX AI Labs☆44Updated 11 months ago
- Explore different way to mix speech model(wav2vec2, hubert) and nlp model(BART,T5,GPT) together☆47Updated last month
- The YouTube Text-To-Speech dataset is comprised of waveform audio extracted from YouTube videos alongside their English transcriptions☆51Updated 4 years ago
- Implementation of CoBERT: Self-Supervised Speech Representation Learning Through Code Representation Learning☆47Updated last year
- LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models☆25Updated last year
- ☆34Updated 4 years ago
- This app is intended to automatically create a corpus for ASR systems using pseudo-labeling.☆27Updated last year
- VoiceBank-2023 is the speech corpus specially designed for constructing personalized Mandarin text-to-speech (TTS) systems.☆39Updated 2 years ago
- ☆14Updated 2 years ago
- PnG BERT: Augmented BERT on Phonemes and Graphemes for Neural TTS☆24Updated 3 years ago
- Hong Kong Cantonese Corpus of transcribed speech (spontaneous speech, radio programmes and a monologue).☆67Updated last year
- ☆88Updated last year
- ☆41Updated 2 years ago
- End-to-end Speech Translation☆35Updated 4 years ago
- [ICASSP‘25] Developing a Multilingual Dataset and Evaluation Metrics for Code-Switching: A Focus on Hong Kong's Polylingual Dynamics☆31Updated 2 weeks ago
- Textless (ASR-transcript free) Spoken Question Answering. The official release of NMSQA dataset and the implementation of "DUAL: Textless…☆35Updated 2 years ago
- Implementation of Google's USM speech model in Pytorch☆30Updated last week