Pytorch implementation for DeepSpeech 2.0
☆31Jul 25, 2024Updated last year
Alternatives and similar repositories for DeepSpeech-pytorch
Users that are interested in DeepSpeech-pytorch are comparing it to the libraries listed below
Sorting:
- PyTorch implementation of "Deep Speech 2: End-to-End Speech Recognition in English and Mandarin" (ICML, 2016)☆26Mar 5, 2021Updated 5 years ago
- Code for the paper "Bag of features for voice anti-spoofing"☆13Jul 6, 2023Updated 2 years ago
- ☆16Oct 7, 2022Updated 3 years ago
- Listen, Attend and spell model for E2E ASR. Implementation in Pytorch☆42Jun 22, 2022Updated 3 years ago
- DropClass and DropAdapt - repository for the paper accepted to Speaker Odyssey 2020☆22Oct 29, 2020Updated 5 years ago
- ☆10Jul 29, 2025Updated 7 months ago
- ☆33Oct 4, 2018Updated 7 years ago
- Kubernetes operator that updates automatically existing deployment's images to the latest version, in a customized way.☆13Aug 31, 2022Updated 3 years ago
- Pytorch实现的流式与非流式的自动语音识别框架，同时兼容在线和离线识别，目前支持Conformer、Squeezeformer、DeepSpeech2模型，支持多种数据增强方法。☆722Dec 17, 2025Updated 2 months ago
- [INTERSPEECH 2023] Knowledge Transfer from Pre-trained Language Models to Cif-based Recognizers via Hierarchical Distillation☆41Sep 1, 2023Updated 2 years ago
- fine-tune Wav2vec2. an ASR model released by Facebook☆36Dec 11, 2021Updated 4 years ago
- 1st place solution to the DCASE 2020 - Task 5 - Urban Sound Tagging with Spatiotemporal Context☆16Dec 8, 2022Updated 3 years ago
- UzTransliterator | State-of-the-art machine transliteration tool for Uzbek language☆13Jan 6, 2026Updated 2 months ago
- ☆11Dec 24, 2024Updated last year
- Language and Speech Technology for Central Kurdish Varieties (LREC-COLING 2024)☆11Nov 29, 2024Updated last year
- Deployed a facial emotion recognition using neural network model which predicts the emotion from faces in images, videos and live feed fr…☆11May 2, 2021Updated 4 years ago
- Spell correction language model for Uyghur language based on transformer neural network☆14Jun 18, 2025Updated 8 months ago
- This repository shows how to implement a basic model for multimodal entailment.☆10Aug 17, 2021Updated 4 years ago
- Sentiment Analysis via RNN, RNTN. Based on Stanford's Sentiment Analysis page.☆10Feb 5, 2015Updated 11 years ago
- PyTorch implementation of automatic speech recognition models.☆38Jan 10, 2021Updated 5 years ago
- Data manipulation and transformation for audio signal processing, powered by PyTorch☆10Sep 30, 2024Updated last year
- A streamable speech recognition model with transformer encoders and RNN-T loss☆11Mar 1, 2021Updated 5 years ago
- One command to start a streaming ASR server.☆12Oct 2, 2024Updated last year
- Python wrapper for the EDDL library.☆13Jun 14, 2022Updated 3 years ago
- Reference implementation and test synthetic data for Sorted Center Time echo density measure for acoustic impulse responses☆15Mar 18, 2020Updated 5 years ago
- A CNN audio classifier via spectrogram images.☆10Jul 21, 2017Updated 8 years ago
- ☆10Nov 10, 2021Updated 4 years ago
- Make N-Gram for Uyghur language☆15Dec 24, 2020Updated 5 years ago
- Speech to text transcription using RNN (Listen, Attend and Spell).☆11Aug 23, 2019Updated 6 years ago
- BigBlueButton API for .NET☆11Sep 12, 2022Updated 3 years ago
- AzukiはC# 2.0で書かれたフリーのテキストエディタエンジンです。オリジナル版を github で fork して拡張版を作成しています。☆11Feb 26, 2023Updated 3 years ago
- A fine multimodality fusion network :)☆11Aug 9, 2021Updated 4 years ago
- there are UKIJ and Uighursoft fonts☆13Oct 21, 2022Updated 3 years ago
- 跨平台网络库，使用epoll和iocp模型☆10May 13, 2018Updated 7 years ago
- Cython implementation of Moattar and Homayounpour's Voice Activity Detection (VAD) algorithm fast enough for real-time on an RPi 3.☆12Aug 18, 2018Updated 7 years ago
- uyghur text resource crawled from website☆12Dec 25, 2015Updated 10 years ago
- FunASR安卓端侧离线版本2pass全模式☆14Sep 4, 2023Updated 2 years ago
- A PyTorch implementation of SimSiam based on CVPR 2021 paper "Exploring Simple Siamese Representation Learning"☆12Mar 23, 2021Updated 4 years ago
- 基于wenet的短时在线语音识别服务☆11Feb 25, 2023Updated 3 years ago