In this repository, we explore model compression for transformer architectures via quantization. We specifically explore quantization aware training of the linear layers and demonstrate the performance for 8 bits, 4 bits, 2 bits and 1 bit (binary) quantization.
☆24May 14, 2021Updated 4 years ago
Alternatives and similar repositories for Compressed-Transformers
Users that are interested in Compressed-Transformers are comparing it to the libraries listed below
Sorting:
- SChunk-Encoder (Transformer or Conformer) for streaming E2E ASR☆11Oct 21, 2022Updated 3 years ago
- Unsupervised speech activity detection system.☆11Jul 2, 2018Updated 7 years ago
- This is an extension of kaldi speech recognition software which allows to perform decoding of speech with hybrid word and phoneme graphs.…☆11Feb 4, 2020Updated 6 years ago
- Implementation of different noise embeddings for noise aware training of Kaldi acoustic models.☆13Feb 13, 2021Updated 5 years ago
- PolEval 2021 Task 1☆15Jun 28, 2022Updated 3 years ago
- ☆14Jun 12, 2015Updated 10 years ago
- ☆30Jan 22, 2026Updated last month
- Crawling and creating a German language model resource☆18Aug 23, 2022Updated 3 years ago
- ☆12Jun 10, 2021Updated 4 years ago
- C++ package for learning optimal wavelet bases using a neural network approach.☆14Dec 2, 2016Updated 9 years ago
- ☆17Oct 16, 2018Updated 7 years ago
- ☆17Jun 30, 2020Updated 5 years ago
- ☆14Jul 11, 2022Updated 3 years ago
- A fork of Idiap Research Institute's DiarTk diarization toolkit☆16Feb 20, 2016Updated 10 years ago
- Example workflow for our data-centric speech benchmark☆17Jul 6, 2023Updated 2 years ago
- Sisyphus recipies for ASR☆19Updated this week
- ☆16Mar 7, 2019Updated 6 years ago
- Artie Bias Corpus: an audio corpus + code for detecting demographic bias☆20Jul 21, 2020Updated 5 years ago
- Consistent dictionary learning algorithm for signal declipping (Python code)☆20Oct 24, 2018Updated 7 years ago
- Official Repository for "Efficient Vocal Source Separation Through Windowed RoFormer"☆43Oct 30, 2025Updated 4 months ago
- This is EllaVator project to build Ella the talking eleVator as part of a Saarland University software project class.☆17Jun 8, 2016Updated 9 years ago
- wake word spotting with kaldi☆19Dec 3, 2020Updated 5 years ago
- Parallelized automatic corpus collection for ASR. Forked from https://github.com/EgorLakomkin/KTSpeechCrawler☆23Mar 21, 2021Updated 4 years ago
- ☆22Jun 30, 2021Updated 4 years ago
- Download and create a tfreader for the audioset dataset☆16Apr 16, 2020Updated 5 years ago
- Implementation of the DIVA model of speech acquisition and production using PyTorch☆22Jan 18, 2023Updated 3 years ago
- This repository is the code and data for DialMed: A Dataset for Dialogue-based Medication Recommendation, COLING 2022.☆23Oct 26, 2022Updated 3 years ago
- DSing ASR task: Resources and Baseline for an unaccompanied singing ASR.☆19Nov 23, 2021Updated 4 years ago
- Audio-JEPA is an adaptation of the Joint-Embedding Predictive Architecture (JEPA) for self-supervised audio representation learning. Buil…☆40Jun 17, 2025Updated 8 months ago
- Source code of paper <End-to-End Language Diarization for Bilingual Code-switching Speech>☆19Jan 23, 2022Updated 4 years ago
- Python implementation of CTC beam search decoder + agnostic LM scorer☆20Dec 16, 2020Updated 5 years ago
- ☆19Nov 4, 2022Updated 3 years ago
- MicRank is a Learning to Rank neural channel selection framework where a DNN is trained to rank microphone channels.☆22Apr 8, 2021Updated 4 years ago
- A baseline Automatic Speech Recognition system for Polish based on Kaldi.☆18Dec 21, 2021Updated 4 years ago
- BurrMill core☆22Nov 2, 2021Updated 4 years ago
- Corpus of oral arguments (recorded speech + official transcripts) of the United States Supreme Court☆22Dec 8, 2022Updated 3 years ago
- An open-source tool for automatic speech recognition ASR quality estimation.☆23Dec 12, 2019Updated 6 years ago
- Official implementation of the paper "SPEAKER VGG CCT: Cross-corpus Speech Emotion Recognition with Speaker Embedding and Vision Transfor…☆24Feb 17, 2023Updated 3 years ago
- Baseline convolutional ASR system in PyTorch☆21Nov 16, 2023Updated 2 years ago