georgian-io / Knowledge-Distillation-Toolkit
[DEPRECATED] A knowledge distillation toolkit based on PyTorch and PyTorch Lightning.
☆136Updated 7 months ago
Related projects: ⓘ
- [ASRU 2021] Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition☆208Updated last year
- ☆51Updated this week
- LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT☆68Updated last year
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition☆69Updated 4 years ago
- Pre-training Cross-modal Transformer for Audio-and-Language Representations☆39Updated 3 years ago
- Composing General Audio Representation by Fusing Multilayer Features of a Pre-trained Model☆26Updated last year
- Official code for Wav2Seq☆95Updated 2 years ago
- Incorporating KenLM language model with HuggingFace implementation of Wav2Vec2CTC Model using beam search decoding☆71Updated 2 years ago
- [NeurIPS'22] Squeezeformer: An Efficient Transformer for Automatic Speech Recognition☆245Updated last year
- The Additive Margin SincNet (AM-SincNet) is a new approach for speaker recognition problems which is based in the neural network architec…☆43Updated 11 months ago
- Small repo describing how to use Hugging Face's Wav2Vec2 with PyCTCDecode☆109Updated 2 years ago
- Code for the Paper Speech Recognition and Multi-Speaker Diarization of Long Conversations☆36Updated last year
- ☆74Updated 2 years ago
- The official repository for Audio ALBERT☆64Updated 2 years ago
- Companion repository for the paper "A Comparison of Metric Learning Loss Functions for End-to-End Speaker Verification" published at SLSP…☆59Updated 3 years ago
- A Pytorch implementation of the paper : SpecAugment++: A Hidden Space Data Augmentation Method for Acoustic Scene Classification☆31Updated 3 years ago
- PyTorch implementation of "Squeezeformer: An Efficient Transformer for Automatic Speech Recognition" (NeurIPS 2022)☆131Updated last year
- A lightweight library to compute Diarization Error Rate (DER).☆59Updated last year
- ASRecognition: just an easy-to-use library for Automatic Speech Recognition.☆51Updated last year
- Additive margin softmax loss in pytorch☆45Updated 5 years ago
- [ICLR 2022] "Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable", by Shaojin Ding, Tianlong Chen, Z…☆30Updated 2 years ago
- Code for the TASLP paper "PSLA: Improving Audio Tagging With Pretraining, Sampling, Labeling, and Aggregation".☆137Updated last year
- Official Implementation of Mockingjay in Pytorch☆52Updated last year
- Making Espnet easier to use☆51Updated 3 years ago
- Example code for a neural transducer model.☆58Updated 7 months ago
- WavEncoder is a Python library for encoding audio signals, transforms for audio augmentation, and training audio classification models wi…☆88Updated 3 years ago
- E2E-SincNet: Toward fully end-to-end speech recognition☆29Updated 4 years ago
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆56Updated last year
- Official implementation of the Keyword Transformer: https://arxiv.org/abs/2104.00769☆121Updated 2 years ago
- PyTorch reimplementation of per-channel energy normalization for audio.☆93Updated 5 years ago