upskyy / Squeezeformer
PyTorch implementation of "Squeezeformer: An Efficient Transformer for Automatic Speech Recognition" (NeurIPS 2022)
☆133Updated 2 years ago
Alternatives and similar repositories for Squeezeformer:
Users that are interested in Squeezeformer are comparing it to the libraries listed below
- [ASRU 2021] Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition☆213Updated last year
- [NeurIPS'22] Squeezeformer: An Efficient Transformer for Automatic Speech Recognition☆249Updated 2 years ago
- PyTorch implementation of "Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss" (ICASS…☆102Updated 2 years ago
- PyTorch implementation of "ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context" (INT…☆34Updated 2 years ago
- A PyTorch implementation of End-to-End Neural Diarization☆102Updated last year
- This is the Python library for an unsupervised, fast method for robust voice activity detection (rVAD), as in the paper rVAD: An Unsuperv…☆131Updated last month
- ☆163Updated 2 years ago
- A torch implementation of a recursion which turns out to be useful for RNN-T.☆140Updated last year
- Transformer implementation speciaized in speech recognition tasks using Pytorch.☆66Updated 3 years ago
- PyTorch implementation of RNN-Transducer(RNN-T).☆75Updated 3 years ago
- LightHuBERT: Lightweight and Configurable Speech Representation Learning with Once-for-All Hidden-Unit BERT☆70Updated 2 years ago
- ☆68Updated 2 years ago
- Example code for a neural transducer model.☆61Updated last year
- 语音识别 论文 前沿☆43Updated 3 years ago
- Official implementation of the Keyword Transformer: https://arxiv.org/abs/2104.00769☆125Updated 2 years ago
- 3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition☆118Updated 2 years ago
- This repo is for the SPL paper "Auto-Tuning Spectral Clustering for Speaker Diarization Using Normalized Maximum Eigengap"☆116Updated 2 years ago
- Libriheavy: a 50,000 hours ASR corpus with punctuation casing and context☆188Updated 5 months ago
- Dynamic Chunk Streaming and Offline Conformer based on athena-team/Athena.☆44Updated 2 years ago
- Dataset and baseline code for the VocalSound dataset (ICASSP2022).☆128Updated 2 years ago
- Official repository for the "Powerset multi-class cross entropy loss for neural speaker diarization" paper published in Interspeech 2023.☆79Updated last year
- Computes the MWER (minimum WER) Loss with CTC beam search. Knowledge distillation for CTC loss.☆57Updated last year
- Official repository of NeXt-TDNN for speaker verification☆65Updated 4 months ago
- The VoxTube dataset official repository☆66Updated last year
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition☆73Updated 4 years ago
- INTERSPEECH 2023: "DPHuBERT: Joint Distillation and Pruning of Self-Supervised Speech Models"☆110Updated last year
- Clustering-based methods for overlapping diarization☆75Updated last year
- A pytorch_lightning reimplementation of the Transducer module from ESPnet.☆75Updated 3 years ago
- Incorporating KenLM language model with HuggingFace implementation of Wav2Vec2CTC Model using beam search decoding☆74Updated 3 years ago
- Research code for the paper "Fine-tuning wav2vec2 for speaker recognition" found at https://arxiv.org/abs/2109.15053☆144Updated 2 years ago