Alternatives and similar repositories for Automatic-Speech-Recognition-from-Scratch

Users that are interested in Automatic-Speech-Recognition-from-Scratch are comparing it to the libraries listed below

• double22a / speech_dataset
  The dataset of Speech Recognition
  ☆446Updated 3 weeks ago
• KeSpeech / KeSpeech
  The repo provides information about KeSpeech dataset.
  ☆170Updated 3 years ago
• Executedone / Chinese-FastSpeech2
  基于标贝数据继续训练，同时对原本的FastSpeech2模型做了改进，引入了韵律表征以及韵律预测模块，使中文发音更生动且富有节奏
  ☆277Updated 2 years ago
• DataXujing / ASR-paper
  ASR教程: https://dataxujing.github.io/ASR-paper/
  ☆25Updated last year
• du-ud / kaldi-cslt
  ☆15Updated 3 years ago
• wenet-e2e / wetts
  Production First and Production Ready End-to-End Text-to-Speech Toolkit
  ☆412Updated 2 months ago
• TowerYsable / ASR_awesome
  语音识别 论文 前沿
  ☆51Updated 4 years ago
• modelscope / kws-training-suite
  ☆146Updated 2 years ago
• wolfparticle / lee-nlp_asr2020
  主要参考李宏毅老师2020年人类语言处理课程资料整理，包括代码和ppt
  ☆33Updated 4 years ago
• SpeechColab / Leaderboard
  SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.
  ☆538Updated 10 months ago
• yeyupiaoling / SpeechEmotionRecognition-Pytorch
  基于Pytorch实现的语音情感识别
  ☆257Updated last month
• double22a / asr_nlp_paper_code
  Papers of ASR, Tools of ASR
  ☆41Updated 11 months ago
• Kevinnan-teen / Speaker-Recognition
  说话人识别（声纹识别）算法的Python实现。包括GMM（已完成）、GMM-UBM、ivector、基于深度学习的声纹识别（self-attention已完成）。
  ☆106Updated 2 years ago
• jackaduma / LAS_Mandarin_PyTorch
  Listen, attend and spell Model and a Chinese Mandarin Pretrained model (中文-普通话 ASR模型)
  ☆124Updated 2 years ago
• MingLunHan / CIF-HieraDist
  [INTERSPEECH 2023] Knowledge Transfer from Pre-trained Language Models to Cif-based Recognizers via Hierarchical Distillation
  ☆41Updated 2 years ago
• datawhalechina / hugging-audio
  Hugging Face Audio Course中文版，帮助学习者快速入门音频模态
  ☆37Updated last year
• wenet-e2e / WenetSpeech
  A 10000+ hours dataset for Chinese speech recognition
  ☆587Updated 3 weeks ago
• yeyupiaoling / PunctuationModel
  中文标点符号模型，可以给文本添加标点符号。
  ☆147Updated last year
• modelscope / FunCodec
  FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music gener…
  ☆442Updated 2 years ago
• ddlBoJack / Awesome-Speech-Language-Model
  Paper, Code and Resources for Speech Language Model and End2End Speech Dialogue System.
  ☆189Updated last year
• yeyupiaoling / MASR
  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。
  ☆718Updated last month
• wenet-e2e / wenet_in_action_homework
  WeNet 实战课程作业
  ☆20Updated 3 years ago
• MooreThreads / MooER
  MooER: Moore-threads Open Omni model for speech-to-speech intERaction. MooER-omni includes a series of end-to-end speech interaction mode…
  ☆219Updated last year
• wenet-e2e / wekws
  Production First and Production Ready End-to-End Keyword Spotting Toolkit
  ☆688Updated 4 months ago
• yingdajun / SpeechEmotionAndPeopleAnalyse
  用CASIA database数据集做的，做的语音情感识别和语音识人的练习
  ☆74Updated 3 years ago
• ddlBoJack / Awesome-Speech-Pretraining
  Paper, Code and Statistics for Self-Supervised Learning and Pre-Training on Speech.
  ☆211Updated 2 years ago
• teamtee / Qwen2-Audio-finetune
  This is a repository for fine-tuning Qwen2-Audio, currently supporting Distributed Data Parallel (DDP) and DeepSpeed.
  ☆48Updated 6 months ago
• qinyuenlp / wav2vec_finetune
  ASR: fine-tune wav2vec 2.0 with transformers
  ☆21Updated 4 years ago
• xinchen-ai / Westlake-Omni
  ☆204Updated last year
• SpeechColab / GigaSpeech2
  An evolving, large-scale and multi-domain ASR corpus for low-resource languages with automated crawling, transcription and refinement
  ☆183Updated 4 months ago