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 3 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☆39Updated last year
- ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription☆28Updated this week
- A High-Quality and Large-Scale Dataset for English-Vietnamese Speech Translation (INTERSPEECH 2022)☆21Updated 9 months ago
- Transformation spoken text to written text☆30Updated 11 months ago
- finetune llm part for spark-tts model☆57Updated last month
- Open TTS models, built for streaming on the edge☆39Updated last month
- Vi_G2P or ViG2P: G2P package for Vietnamese: based on vPhon and phonology knowledge to convert Raw text - Graphoneme to IPA☆82Updated 10 months ago
- ☆45Updated 7 months ago
- ☆50Updated last year
- python script to download & process data to train a speech-synthesis model of Vietnamese M.C. Nguyễn Ngọc Ngạn☆12Updated 8 months ago
- Vietnamese Voice Cloning System using Speaker Verification training on multispeaker VITS☆52Updated last year
- Provide Gradio custom components to make the diarization-based audio labeling process easier and faster.☆62Updated 2 weeks ago
- End-to-End Vietnamese Speech Recognition using wav2vec 2.0☆98Updated 3 years ago
- This is an implementation for train hifigan part of XTTSv2 model using Coqui/TTS.☆72Updated 5 months ago
- Python - NSW package for Vietnamese: Normalization system to convert numbers, abbreviations, and words that cannot be pronounced into syl…☆59Updated 3 months ago
- ☆88Updated 2 weeks ago
- Solution for Zalo AI Challenge 2022 - Lyrics Alignment☆68Updated 2 years ago
- A Python library for text normalization, specifically designed for Vietnamese and English text processing. This library provides comprehe…☆10Updated 3 weeks ago
- Official repo for the Vietnam-Celeb dataset☆20Updated last year
- ☆27Updated 3 weeks ago
- Speaker change detection using SincNet and an LSTM/Transformer☆50Updated 9 months ago
- Whisper Speaker Identification (WSI), a cutting-edge model for multilingual speaker identification.☆14Updated last month
- ☆84Updated last year
- ☆20Updated 2 years ago
- This is a fork of the original fairseq repository (version 0.12.2) with added classes for training mHuBERT-147.☆17Updated 5 months ago
- A synthesized dataset for Vietnamese TTS task☆62Updated 2 years ago
- Official repository for the "Powerset multi-class cross entropy loss for neural speaker diarization" paper published in Interspeech 2023.☆81Updated last year
- Vietnamese Punctuation Prediction using Pretrained Language Models☆13Updated 2 years ago
- VietTTS: An Open-Source Vietnamese Text to Speech☆48Updated 4 months ago
- Dippy Synthetic Speech Subnet☆16Updated 3 weeks ago