navana-tech / baseline_recipe_is21s_indic_asr_challenge
Multilingual and code-switching ASR challenges for low resource Indian languages.
☆20Updated 3 years ago
Alternatives and similar repositories for baseline_recipe_is21s_indic_asr_challenge:
Users that are interested in baseline_recipe_is21s_indic_asr_challenge are comparing it to the libraries listed below
- This repository describes our reproducible framework for assessing self-supervised representation learning from speech☆51Updated 3 years ago
- Rescoring methods for end-to-end Automatic Speech Recognition☆27Updated 4 years ago
- ☆35Updated last month
- Data and code related to the ICASSP submission "A comparison of methods for OOV-word recognition"☆17Updated 3 years ago
- Phonetically-Oriented Word Error Rate☆34Updated 5 years ago
- CMU multilingual speech repository☆31Updated 3 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 5 years ago
- An adaptation of Fairseq to (End-to-end) speech translation.☆22Updated 2 years ago
- Pypi installable TDNN and TDNN-F layers for PyTorch based acoustic model training☆39Updated 4 years ago
- Pronunciation-assisted Subword Modeling☆29Updated 5 years ago
- An implementation of RNN-Transducer loss in TF-2.0.☆45Updated 2 years ago
- Kaldi style neural network training in pytorch for use in place of nnet3 in Kaldi.☆26Updated 8 months ago
- Incorporating KenLM language model with HuggingFace implementation of Wav2Vec2CTC Model using beam search decoding☆75Updated 3 years ago
- ☆16Updated 2 years ago
- Implementation of the paper "Confidence estimation for attention based sequence to sequence models for speech recognition"☆16Updated 3 years ago
- Analysis and investigating the confounding effect of accents in end-to-end Automatic Speech Recognition models.☆15Updated 4 years ago
- ☆17Updated 2 years ago
- Dynamic Chunk Streaming and Offline Conformer based on athena-team/Athena.☆44Updated 2 years ago
- Code repository for the paper "Improving End-to-End SLU performance with Prosodic Attention and Distillation" accepted at Interspeech 202…☆25Updated last year
- BERT and LSTM baseline models of the ZeroSpeech Challenge 2021☆59Updated 2 years ago
- Example code for a neural transducer model.☆61Updated last year
- Confidence Estimation for Black Box Automatic Speech Recognition Systems Using Lattice Recurrent Neural Networks https://arxiv.org/abs/19…☆16Updated 5 years ago
- Python wrapper for kaldi's arpa2fst☆38Updated 4 months ago
- Lattice combination algorithm to combine inaccurate transcripts with hypothesis lattices☆16Updated last year
- A Full Text-Dependent End to End Mispronunciation Detection and Diagnosis with Easy Data Augment Techniques☆59Updated 3 years ago
- E2E-SincNet: Toward fully end-to-end speech recognition☆30Updated 5 years ago
- Compendium for the paper "Transparent pronunciation scoring using articulatorily weighted phoneme edit distance" by Karhila, Smolander, Y…☆25Updated 5 years ago
- Implementation of the paper "BERTphone: Phonetically-aware Encoder Representations for Utterance-level Speaker and Language Recognition"☆17Updated 4 years ago
- This repository contains data used in the NAACL 2021 Paper - Proteno: Text Normalization with Limited Data for Fast Deployment in Text to…☆45Updated 3 years ago
- Python wrappers for Kaldi Levenshtein's distance and alignment code.☆63Updated last year