AI4Bharat / vistaarLinks
Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR
☆65Updated 6 months ago
Alternatives and similar repositories for vistaar
Users that are interested in vistaar are comparing it to the libraries listed below
Sorting:
- Pretraining, fine-tuning and evaluation scripts for Indic-Wav2Vec2☆101Updated 3 months ago
- NPTEL2020: Speech2Text dataset for Indian-English Accent☆77Updated 3 years ago
- ☆44Updated 2 years ago
- ☆49Updated 3 years ago
- A python package for whisper normalizer☆70Updated 2 months ago
- This project is about performing Speaker diarization for Hindi Language.☆56Updated 4 years ago
- Towards Building Text-To-Speech Systems for the Next Billion Users - Microsoft Research Intern Work - Accepted at ICASSP 2023☆55Updated 2 years ago
- Swarah: Indian-English speech dataset collected across the country☆36Updated 5 months ago
- Promting Whisper for Audio-Visual Speech Recognition, Code-Switched Speech Recognition, and Zero-Shot Speech Translation☆151Updated last year
- ☆17Updated 4 years ago
- Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.☆352Updated 2 years ago
- Repository containing experimentation platform on how to train, infer on wav2vec2 models.☆87Updated 3 years ago
- Finetune VITS and MMS using HuggingFace's tools☆180Updated last year
- Official repository for the "Powerset multi-class cross entropy loss for neural speaker diarization" paper published in Interspeech 2023.☆91Updated 2 years ago
- Various speech datasets made available to the public☆129Updated 11 months ago
- ☆47Updated 5 months ago
- Traditional ASR (Signal & Cepstral Analysis, DTW, HMM) & DNNs (Custom Models + DeepSpeech) on Indian Accent Speech☆92Updated 2 years ago
- ☆157Updated 3 weeks ago
- This repository contains the training, inference, evaluation code for SpeechLLM models and details about the model releases on huggingfac…☆124Updated last year
- ☆60Updated 5 months ago
- Whisper finetuned on VinBigdata-VLSP2020-100h + KenLM☆37Updated 2 years ago
- An implementation of the paper titled "Arabic Speech Emotion Recognition Employing Wav2vec2.0 and HuBERT Based on BAVED Dataset" https://…☆13Updated 3 years ago
- Speaker change detection using SincNet and an LSTM/Transformer☆56Updated 6 months ago
- Indic TTS for Indian Languages: This is a project on developing text-to-speech (TTS) synthesis systems for Indian languages, improving qu…☆50Updated 3 weeks ago
- Hosts text-to-speech corpus and speech synthesizers for African languages.☆17Updated 2 years ago
- Stable timestamps and confidence score for words of OpenAI's Whisper outputs down to word-level.☆25Updated 2 years ago
- Voice Activity Projection Models: Self-supervised learning of Turn-taking Events☆86Updated last year
- Dataset Release for Intent Classification from Speech☆48Updated 9 months ago
- EMNLP 23 - Integrating Whisper Encoder to LLaMA Decoder for Generative ASR Error Correction☆264Updated last year
- An easy way to fine-tune Wav2Vec 2.0 for low-resource languages.☆81Updated 2 years ago