kssteven418 / Q-ASR
[ICASSP'22] Integer-only Zero-shot Quantization for Efficient Speech Recognition
☆31Updated 3 years ago
Alternatives and similar repositories for Q-ASR:
Users that are interested in Q-ASR are comparing it to the libraries listed below
- Pytorch implementation of BiFSMN, IJCAI 2022☆21Updated 2 years ago
- In this repository, we explore model compression for transformer architectures via quantization. We specifically explore quantization awa…☆23Updated 3 years ago
- Pytorch implementation of BiFSMNv2, TNNLS 2023☆30Updated 2 years ago
- ☆43Updated last year
- ☆19Updated 5 years ago
- FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learning (INTERSPEECH 2022)☆17Updated last year
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆57Updated last year
- Test Framework for few-shot open set KWS☆27Updated 3 months ago
- Multi-Head-Attention RNN pytorch implement for keyword spotting☆21Updated 4 years ago
- TernGEMM: General Matrix Multiply Library with Ternary Weights for Fast DNN Inference☆13Updated 3 years ago
- Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva☆82Updated last week
- ☆55Updated last year
- This repository containts the pytorch scripts to train mixed-precision networks for microcontroller deployment, based on the memory contr…☆49Updated 9 months ago
- [ICLR 2022] "Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable", by Shaojin Ding, Tianlong Chen, Z…☆30Updated 2 years ago
- LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT☆70Updated 2 years ago
- Mining effective negative training samples for keyword spotting (PyTorch)☆59Updated 4 years ago
- ☆25Updated 4 months ago
- Memory efficient transducer loss computation☆68Updated 2 years ago
- Torch-based tool for quantizing high-dimensional vectors using additive codebooks☆51Updated 2 years ago
- Implementation of CTC alignment-based single step non-autoregressive transformer☆13Updated last year
- ☆202Updated 3 years ago
- PyTorch implementation of Continuous Speech Separation☆13Updated 2 years ago
- Implementaion RNN tranceducer☆21Updated 5 years ago
- Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming☆34Updated last year
- ☆16Updated 2 years ago
- Source Code for the Paper "UNIFIED KEYWORD SPOTTING AND AUDIO TAGGING ON MOBILE DEVICES WITH TRANSFORMERS"☆23Updated last year
- SpeechNAS-Better-Trade-off-between-Latency-and-Accuracy-for-Large-Scale-Speaker-Verification☆30Updated last year
- [NeurIPS 2022] "Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Spee…☆16Updated last year
- Small compression utility☆35Updated 8 months ago
- ☆15Updated 2 months ago