xiabingquan / Automatic-Speech-Recognition-from-Scratch
An minimal Seq2Seq example of Automatic Speech Recognition (ASR) based on Transformer
☆46Updated 6 months ago
Related projects ⓘ
Alternatives and complementary repositories for Automatic-Speech-Recognition-from-Scratch
- ASR教程: https://dataxujing.github.io/ASR-paper/☆23Updated 4 months ago
- 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☆247Updated last year
- 基于Pytorch的Conformer语音识别模型实现☆8Updated last year
- Hugging Face Audio Course中文版,帮助学习者快速入门音频模态☆31Updated 5 months ago
- The dataset of Speech Recognition☆387Updated 4 months ago
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆371Updated 5 months ago
- Production First and Production Ready End-to-End Keyword Spotting Toolkit☆457Updated 3 months ago
- 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)。☆73Updated last year
- 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☆32Updated 3 years ago
- SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.☆443Updated 2 months ago
- 针对CN-Celeb数据集的基于ECAPA-TDNN的说话人识别的pytorch实现☆9Updated last year
- 语音方向实验室/公司/资源/实习等,欢迎推荐或自荐☆517Updated 2 weeks ago
- 语音识别 论文 前沿☆43Updated 2 years ago
- Unoffical implementation of Megatts2☆264Updated 7 months ago
- 端到端语音唤醒工具箱,从模型训练到模型推理。☆73Updated 2 months 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。☆617Updated this week
- ☆15Updated 2 years ago
- Audio Split 基于双门限法的语音端点检测及语音分割☆127Updated 4 years ago
- The repo provides information about KeSpeech dataset.☆113Updated 2 years ago
- Papers of ASR, Tools of ASR☆38Updated last year
- 本项目是基于Pytorch的语音合成项目,使用的是VITS,VITS是一种语音合成方法,这种时端到端的模型使用起来非常简单,不需要文本对齐等太复杂的流程,直接一键训练和生成,大大降低了学习门槛。☆38Updated 2 months ago
- FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music gener…☆369Updated 9 months ago
- ☆80Updated last year
- 一个执着于让CPU\端侧-Model逼近GPU-Model性能的项目,CPU上的实时率(RTF)小于0.1☆461Updated last month
- Listen, attend and spell Model and a Chinese Mandarin Pretrained model (中文-普通话 ASR模型)☆121Updated last year
- 中文数字语音识别:识别类语音验证码的8位数字语音☆9Updated 4 years ago
- A enterprise-grade Voice Activity Detector from modelscope and funasr.☆61Updated last year
- ☆142Updated 4 years ago
- 基于Pytorch实现的语音情感识别☆132Updated 2 months ago
- 中文标点符号模型,可以给文本添加标点符号。☆130Updated 8 months ago