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
- Data and code related to the ICASSP submission "A comparison of methods for OOV-word recognition"☆17Updated 3 years ago
- ☆34Updated 5 months ago
- Analysis and investigating the confounding effect of accents in end-to-end Automatic Speech Recognition models.☆14Updated 4 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
- Phonetically-Oriented Word Error Rate☆33Updated 5 years ago
- Rescoring methods for end-to-end Automatic Speech Recognition☆27Updated 4 years ago
- An implementation of RNN-Transducer loss in TF-2.0.☆45Updated last year
- An adaptation of Fairseq to (End-to-end) speech translation.☆22Updated 2 years ago
- Lattice combination algorithm to combine inaccurate transcripts with hypothesis lattices☆16Updated 11 months ago
- CMU multilingual speech repository☆31Updated 2 years ago
- Pronunciation-assisted Subword Modeling☆29Updated 5 years ago
- Baseline kaldi script for UA-SPEECH corpus☆29Updated 4 months ago
- The repo contains our code of ``Semantic Mask for Transformer based End-to-End Speech Recognition"☆38Updated 4 years ago
- Python wrappers for Kaldi Levenshtein's distance and alignment code.☆62Updated 11 months ago
- Code repository for the paper "Improving End-to-End SLU performance with Prosodic Attention and Distillation" accepted at Interspeech 202…☆24Updated last year
- Incorporating KenLM language model with HuggingFace implementation of Wav2Vec2CTC Model using beam search decoding☆74Updated 3 years ago
- ☆16Updated 2 years ago
- A collection of papers related to speech model compression☆24Updated last year
- End-to-End Mispronunciation Detection via wav2vec2.0☆43Updated 3 years ago
- Kaldi style neural network training in pytorch for use in place of nnet3 in Kaldi.☆26Updated 6 months ago
- ☆12Updated 3 years ago
- E2E-SincNet: Toward fully end-to-end speech recognition☆29Updated 5 years ago
- Example code for a neural transducer model.☆61Updated last year
- BERT and LSTM baseline models of the ZeroSpeech Challenge 2021☆57Updated 2 years ago
- Improving Disfluency Detection by Self-Training a Self-Attentive Model☆47Updated 3 years ago
- Implementation of the paper "BERTphone: Phonetically-aware Encoder Representations for Utterance-level Speaker and Language Recognition"☆17Updated 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
- Pypi installable TDNN and TDNN-F layers for PyTorch based acoustic model training☆39Updated 4 years ago
- Properly handle position-dependent phones in a subword lexicon FST☆31Updated 4 years ago