navana-tech / baseline_recipe_is21s_indic_asr_challenge
Multilingual and code-switching ASR challenges for low resource Indian languages.
☆20Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for baseline_recipe_is21s_indic_asr_challenge
- This repository describes our reproducible framework for assessing self-supervised representation learning from speech☆51Updated 3 years ago
- Data and code related to the ICASSP submission "A comparison of methods for OOV-word recognition"☆17Updated 2 years ago
- ☆32Updated 2 months ago
- Rescoring methods for end-to-end Automatic Speech Recognition☆27Updated 4 years ago
- Lattice combination algorithm to combine inaccurate transcripts with hypothesis lattices☆16Updated 8 months ago
- Python wrappers for Kaldi Levenshtein's distance and alignment code.☆61Updated 8 months ago
- An implementation of RNN-Transducer loss in TF-2.0.☆45Updated last year
- Incorporating KenLM language model with HuggingFace implementation of Wav2Vec2CTC Model using beam search decoding☆71Updated 3 years ago
- ☆12Updated 3 years ago
- Implementation of the paper "Confidence estimation for attention based sequence to sequence models for speech recognition"☆15Updated 3 years ago
- Phonetically-Oriented Word Error Rate☆33Updated 5 years ago
- An example directory for running Multi-Task Learning training on Kaldi neural networks. In Kaldi-speak, this is an egs dir for nnet3 trai…☆54Updated 4 years ago
- Analysis and investigating the confounding effect of accents in end-to-end Automatic Speech Recognition models.☆13Updated 4 years ago
- Confidence Estimation for Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural Networks https://arxiv.org/abs/19…☆16Updated 4 years ago
- Experiments on speech recognition robustness to accents and dialects☆12Updated 5 years ago
- Pronunciation-assisted Subword Modeling☆29Updated 5 years ago
- Python wrapper for kaldi's arpa2fst☆38Updated last year
- ☆16Updated 2 years ago
- Pypi installable TDNN and TDNN-F layers for PyTorch based acoustic model training☆38Updated 3 years ago
- Kaldi style neural network training in pytorch for use in place of nnet3 in Kaldi.☆26Updated 3 months ago
- Multistream CNN for Robust Acoustic Modeling☆39Updated 3 years ago
- The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"☆37Updated 4 years ago
- ☆27Updated 3 years ago
- Recurrent Neural Aligner☆49Updated 4 years ago
- E2E-SincNet: Toward fully end-to-end speech recognition☆29Updated 4 years ago
- CMU multilingual speech repository☆31Updated 2 years ago
- BERT and LSTM baseline models of the ZeroSpeech Challenge 2021☆57Updated 2 years ago
- ☆16Updated 2 years ago
- Code repository for the paper "Improving End-to-End SLU performance with Prosodic Attention and Distillation" accepted at Interspeech 202…☆23Updated last year