menloresearch / WhisperSpeech
Ichigo Whisper is a compact (22M parameters), open-source speech tokenizer for the Whisper-medium, designed to enhance performance on multilingual with minimal impact on its original English capabilities.
☆15Updated 2 months ago
Alternatives and similar repositories for WhisperSpeech:
Users that are interested in WhisperSpeech are comparing it to the libraries listed below
- Whisper finetuned on VinBigdata-VLSP2020-100h + KenLM☆38Updated last year
- A High-Quality and Large-Scale Dataset for English-Vietnamese Speech Translation (INTERSPEECH 2022)☆21Updated 8 months ago
- Transformation spoken text to written text☆30Updated 10 months ago
- ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription☆20Updated last month
- Vi_G2P or ViG2P: G2P package for Vietnamese: based on vPhon and phonology knowledge to convert Raw text - Graphoneme to IPA☆80Updated 9 months ago
- Vietnamese Voice Cloning System using Speaker Verification training on multispeaker VITS☆51Updated last year
- Solution for Zalo AI Challenge 2022 - Lyrics Alignment☆69Updated 2 years ago
- Python - NSW package for Vietnamese: Normalization system to convert numbers, abbreviations, and words that cannot be pronounced into syl…☆56Updated 2 months ago
- This is an implementation for train hifigan part of XTTSv2 model using Coqui/TTS.☆71Updated 4 months ago
- ☆49Updated last year
- End-to-End Vietnamese Speech Recognition using wav2vec 2.0☆98Updated 3 years ago
- Use LoRA technique to improve training Large Language Model☆12Updated last year
- ☆44Updated 7 months ago
- ☆84Updated last week
- Vietnamese Punctuation Prediction using Pretrained Language Models☆13Updated 2 years ago
- Official repo for the Vietnam-Celeb dataset☆20Updated last year
- Bud500: A Comprehensive Vietnamese ASR Dataset☆65Updated last year
- ☆66Updated 10 months ago
- ☆26Updated last year
- A fine-tuned Large Language Model (LLM) for the Vietnamese language based on the Llama 2 model.☆15Updated last year
- Provide Gradio custom components to make the diarization-based audio labeling process easier and faster.☆60Updated 2 weeks ago
- Vietnamese self-supervised Wav2vec2 model☆61Updated 2 years ago
- Vistral-V: Visual Instruction Tuning for Vistral - Vietnamese Large Vision-Language Model.☆22Updated 8 months ago
- ViSen is library to format tone of Vietnamese sentences☆19Updated 3 years ago
- Xây dựng tập dữ liệu 500GB (20% done) văn bản tiếng Việt để huấn luyện mô hình ngôn ngữ lớn☆25Updated last year
- This repo aims to build a web app that supports speech recognition system It's simple to use and understand☆38Updated last year
- Open TTS models, built for streaming on the edge☆39Updated 2 weeks ago
- Vietnamese long form question answering system with documents retrieval.☆20Updated last year
- ☆84Updated 11 months ago
- This is the official repository for Vista dataset - A Vietnamese multimodal dataset contains more than 700,000 samples of conversations a…☆25Updated 10 months ago