SamsungLabs / SummaryMixing
This repository implements SummaryMixing, a simpler, faster and much cheaper replacement to self-attention for automatic speech recognition (see: https://arxiv.org/abs/2307.07421). The code is ready to be used with the SpeechBrain toolkit).
☆115Updated 4 months ago
Alternatives and similar repositories for SummaryMixing:
Users that are interested in SummaryMixing are comparing it to the libraries listed below
- ☆56Updated 2 years ago
- ☆84Updated 10 months ago
- Official code for Wav2Seq☆96Updated 2 years ago
- Example code for a neural transducer model.☆61Updated last year
- LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT☆70Updated 2 years ago
- ☆69Updated 2 months ago
- Transcribing Speech with Multinomial Diffusion, training code and models.☆76Updated last year
- Speech-MASSIVE is a multilingual Spoken Language Understanding (SLU) dataset comprising the speech counterpart for a portion of the MASSI…☆21Updated 5 months ago
- Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context☆188Updated 5 months ago
- Zero-shot Domain-sensitive Speech Recognition with Prompt-conditioning Fine-tuning (ASRU2023)☆27Updated last year
- DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning☆47Updated last year
- Code for the paper: GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities☆107Updated 2 months ago
- Official repository for the "Powerset multi-class cross entropy loss for neural speaker diarization" paper published in Interspeech 2023.☆79Updated last year
- This Repository surveys the paper focusing on Prompting and Adapters for Speech Processing.☆107Updated last year
- Python wrappers for Kaldi Levenshtein's distance and alignment code.☆62Updated 10 months ago
- BERT and LSTM baseline models of the ZeroSpeech Challenge 2021☆57Updated 2 years ago
- Implementation of BEST-RQ - a model for self-supervised learning of speech signals using a random projection quantizer, in Pytorch.☆111Updated last year
- NOTSOFAR-1 Challenge: Distant Diarization and ASR☆48Updated this week
- Feature extractor for DL speech processing.☆65Updated 2 years ago
- Confidence interval computation for evaluation in machine learning using the bootstrapping approach☆77Updated 10 months ago
- ConMamba for Automatic Speech Recognition☆56Updated 6 months ago
- (Interspeech 2023 & ICASSP 2024) Official repository for ARMHuBERT and STaRHuBERT☆38Updated 5 months ago
- ☆163Updated 2 years ago
- ☆34Updated 5 months ago
- NPTEL2020: Speech2Text dataset for Indian-English Accent☆72Updated 3 years ago
- Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva☆83Updated 2 months ago
- Reference-aware automatic speech evaluation toolkit☆142Updated 2 months ago
- Layer-wise analysis of self-supervised pre-trained speech representations☆100Updated 3 months ago
- A torch implementation of a recursion which turns out to be useful for RNN-T.☆140Updated last year
- Clustering-based methods for overlapping diarization☆75Updated last year