TencentGameMate / chinese_speech_pretrain
chinese speech pretrained models
☆1,106Updated 8 months ago
Alternatives and similar repositories for chinese_speech_pretrain:
Users that are interested in chinese_speech_pretrain are comparing it to the libraries listed below
- The dataset of Speech Recognition☆413Updated 4 months ago
- SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.☆486Updated 3 weeks ago
- A 10000+ hours dataset for Chinese speech recognition☆528Updated last year
- Text Normalization & Inverse Text Normalization☆569Updated 5 months ago
- Production First and Production Ready End-to-End Keyword Spotting Toolkit☆540Updated 2 months ago
- KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at https://modelscope.cn/models?page=1&tasks=text-…☆507Updated last year
- 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。☆666Updated last week
- 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☆261Updated last year
- Chinese voice corpus. 中文语音语料，语音更加清晰自然，包含8个开源数据集，3200个说话人，900小时语音，1300万字。☆638Updated 4 years ago
- [ACL 2024] Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training fo…☆815Updated 4 months ago
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆387Updated 10 months ago
- Chinese text normalization for speech processing☆658Updated 2 years ago
- Chinese Mandarin tts text-to-speech 中文 (普通话) 语音 合成 , by fastspeech 2 , implemented in pytorch, using waveglow as vocoder, with biaobei …☆473Updated 2 years ago
- 这是一个用C++实现ASR推理的项目，它依赖很少，安装也很简单，推理速度很快，在树莓派4B等ARM平台也可以流畅的运行。 支持的模型是由Google的Transformer模型中优化而来，数据集是开源wenetspeech(10000+小时)或阿里私有数据集(60000+小…☆510Updated 2 years ago
- ☆684Updated 10 months ago
- Best practice TTS based on BERT and VITS with some Natural Speech Features Of Microsoft; Support ONNX streaming out!☆1,184Updated 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☆473Updated last month
- ☆1,078Updated this week
- 本项目使用了EcapaTdnn、ResNetSE、ERes2Net、CAM++等多种先进的声纹识别模型，同时本项目也支持了MelSpectrogram、Spectrogram、MFCC、Fbank等多种数据预处理方法☆266Updated last week
- Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit☆882Updated 2 months ago
- This project uses a variety of advanced voiceprint recognition models such as EcapaTdnn, ResNetSE, ERes2Net, CAM++, etc. It is not exclud…☆958Updated last week
- 📣 商用级开源语音自动识别程序库，开箱即用，全平台支持，中英文混合识别。A Cross-platform implementation of ASR inference. It's based on ONNXRuntime and FunASR. We provide …☆545Updated 11 months ago
- tacotronV2 + wavernn 实现中文语音合成(Tensorflow + pytorch)☆535Updated last year
- 基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型☆854Updated last week
- speech-aligner，是一个从“人声语音”及其“语言文本”，产生音素级别时间对齐标注的工具。speech-aligner, is a tool that generate phoneme-level alignment between human speech an…☆401Updated 5 years ago
- Pseudo Streaming SenseVoice with Hotwords☆254Updated last month
- 使用vllm加速cosyvoice2的推理☆232Updated last week
- Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training wit…☆262Updated 3 weeks ago
- Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training wit…☆1,013Updated last week
- An Open Source Tools for Speaker Recognition☆613Updated 8 months ago