kssteven418 / Q-ASR
[ICASSP'22] Integer-only Zero-shot Quantization for Efficient Speech Recognition
☆30Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for Q-ASR
- In this repository, we explore model compression for transformer architectures via quantization. We specifically explore quantization awa…☆22Updated 3 years ago
- FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learning (INTERSPEECH 2022)☆17Updated 11 months ago
- Pytorch implementation of BiFSMN, IJCAI 2022☆21Updated last year
- ☆41Updated last year
- Multi-Head-Attention RNN pytorch implement for keyword spotting☆21Updated 3 years ago
- LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT☆69Updated 2 years ago
- Pytorch implementation of BiFSMNv2, TNNLS 2023☆29Updated last year
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆57Updated last year
- ☆46Updated last year
- [ICLR 2022] "Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable", by Shaojin Ding, Tianlong Chen, Z…☆30Updated 2 years ago
- Test Framework for few-shot open set KWS☆24Updated 2 weeks ago
- TernGEMM: General Matrix Multiply Library with Ternary Weights for Fast DNN Inference☆13Updated 2 years ago
- ☆20Updated 4 years ago
- Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva☆80Updated 2 months ago
- Memory efficient transducer loss computation☆68Updated 2 years ago
- Collection of PyTorch implementations of Spoken Keyword Spotting presented in research papers.☆20Updated 7 months ago
- Broadcasted Residual Learning for Efficient Keyword Spotting☆23Updated 3 years ago
- ☆13Updated 3 months ago
- ☆25Updated last week
- Improving Recording Device Generalization using Impulse Response Augmentation☆10Updated last year
- Implementation of CTC alignment-based single step non-autoregressive transformer☆12Updated last year
- Torch-based tool for quantizing high-dimensional vectors using additive codebooks☆50Updated 2 years ago
- WarpRNNT loss ported in Numba CPU/CUDA for Pytorch☆16Updated 2 years ago
- [ICASSP 2023] FedAudio: A Federated Learning Benchmark for Audio and Speech Tasks☆46Updated 8 months ago
- Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming☆32Updated last year
- Rainbow Keywords - Official PyTorch Implementation☆12Updated 4 months ago
- Continual Learning Benchmark for Spoken Keyword Spotting☆15Updated 2 years ago
- Implementaion RNN tranceducer☆21Updated 5 years ago