AI4Bharat / vistaarLinks
Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR
☆69Updated 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 4 months ago
- ☆49Updated 3 years ago
- A python package for whisper normalizer☆71Updated 2 months ago
- ☆45Updated 3 years ago
- NPTEL2020: Speech2Text dataset for Indian-English Accent☆79Updated 4 years ago
- Promting Whisper for Audio-Visual Speech Recognition, Code-Switched Speech Recognition, and Zero-Shot Speech Translation☆151Updated last year
- Repository containing experimentation platform on how to train, infer on wav2vec2 models.☆87Updated 3 years ago
- Swarah: Indian-English speech dataset collected across the country☆37Updated 5 months ago
- This project is about performing Speaker diarization for Hindi Language.☆58Updated 4 years ago
- ☆17Updated 4 years ago
- Text to Speech for Indic languages☆52Updated 3 years ago
- Official repository for the "Powerset multi-class cross entropy loss for neural speaker diarization" paper published in Interspeech 2023.☆92Updated 2 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
- Finetune VITS and MMS using HuggingFace's tools☆184Updated last year
- Various speech datasets made available to the public☆130Updated last year
- Speaker change detection using SincNet and an LSTM/Transformer☆56Updated 7 months ago
- Traditional ASR (Signal & Cepstral Analysis, DTW, HMM) & DNNs (Custom Models + DeepSpeech) on Indian Accent Speech☆92Updated 2 years ago
- Voice Activity Projection Models: Self-supervised learning of Turn-taking Events☆89Updated last year
- Mispronunciation Detection using a pretrained and finetuned wav2vec2 model for phoneme recognition and diagnosis and feedback using large…☆43Updated last year
- Dataset Release for Intent Classification from Speech☆48Updated 10 months ago
- A Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS☆52Updated last year
- ☆60Updated 5 months ago
- Hosts text-to-speech corpus and speech synthesizers for African languages.☆17Updated 2 years ago
- Fine-tune and evaluate Whisper models for Automatic Speech Recognition (ASR) on custom datasets or datasets from huggingface.☆356Updated 2 years ago
- 🌼 Daisy-TTS: Simulating Wider Spectrum of Emotions via Prosody Embedding Decomposition☆14Updated last month
- Indic TTS for Indian Languages: This is a project on developing text-to-speech (TTS) synthesis systems for Indian languages, improving qu…☆15Updated last year
- ☆156Updated 3 weeks ago
- ☆319Updated last year
- The official implementation of the method discussed in the paper Improving Spoken Language Identification with Map-Mix(work accepted at I…☆18Updated 2 years ago
- This repository contains the training, inference, evaluation code for SpeechLLM models and details about the model releases on huggingfac…☆125Updated last year