AI4Bharat / SvarahLinks
Swarah: Indian-English speech dataset collected across the country
☆34Updated 2 years ago
Alternatives and similar repositories for Svarah
Users that are interested in Svarah are comparing it to the libraries listed below
Sorting:
- NPTEL2020: Speech2Text dataset for Indian-English Accent☆77Updated 3 years ago
- ☆46Updated 2 years ago
- ☆17Updated 4 years ago
- asr2k☆50Updated last year
- Prosodic Speech Segmentation with Transformers☆25Updated last year
- ☆37Updated last month
- Code for AccentDB.☆22Updated 4 years ago
- pytorch implementation for MultiSpeech: Multi-Speaker Text to Speech with Transformer paper☆21Updated 3 years ago
- Rescoring methods for end-to-end Automatic Speech Recognition☆27Updated 4 years ago
- Speaker change detection using SincNet and an LSTM/Transformer☆52Updated last month
- ☆38Updated 3 years ago
- A handy dataset of noises for ASR☆21Updated 6 years ago
- A python package for whisper normalizer☆62Updated last week
- Incorporating KenLM language model with HuggingFace implementation of Wav2Vec2CTC Model using beam search decoding☆75Updated 3 years ago
- Code for the method proposed in the paper:- ccc-wav2vec 2.0: Clustering aided Cross-Contrastive learning of Self-Supervised speech repres…☆21Updated last year
- A toolkit to calculate speech audio quality. Not affiliated with the original authors☆52Updated 10 months ago
- Pypi installable TDNN and TDNN-F layers for PyTorch based acoustic model training☆40Updated 4 years ago
- ☆12Updated 4 months ago
- PyTorch Implementation of Google's Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions. This implementation supp…☆48Updated last year
- Multilingual and code-switching ASR challenges for low resource Indian languages.☆20Updated 3 years ago
- Lattice combination algorithm to combine inaccurate transcripts with hypothesis lattices☆16Updated last year
- Clustering-based methods for overlapping diarization☆80Updated last year
- ☆17Updated 2 years ago
- Balanced Error Rate for Speaker Diarization☆32Updated 2 years ago
- Kaldi style neural network training in pytorch for use in place of nnet3 in Kaldi.☆26Updated 11 months ago
- A Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS☆42Updated 6 months ago
- This app is intended to automatically create a corpus for ASR systems using pseudo-labeling.☆27Updated last year
- Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR☆58Updated 2 weeks ago
- This repo contains the baseline model recipes and pre-trained model for GramVanni hindi ASR challenge☆15Updated 3 years ago
- Example code for a neural transducer model.☆62Updated last year