wenet-e2e / WeTextProcessingLinks
Text Normalization & Inverse Text Normalization
☆642Updated last month
Alternatives and similar repositories for WeTextProcessing
Users that are interested in WeTextProcessing are comparing it to the libraries listed below
Sorting:
- SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech Recognition.☆516Updated 5 months ago
- Chinese text normalization for speech processing☆703Updated 2 years ago
- A 10000+ hours dataset for Chinese speech recognition☆559Updated 2 years 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-…☆519Updated last year
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆394Updated last year
- The dataset of Speech Recognition☆424Updated 8 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☆270Updated last year
- chinese speech pretrained models☆1,159Updated last year
- ☆755Updated last year
- 使用vllm加速cosyvoice2的推理☆406Updated 4 months ago
- Production First and Production Ready End-to-End Keyword Spotting Toolkit☆605Updated last week
- OSUM & OSUM-EChat, open speech understanding model and empathetic spoken chatbot based on it, open-sourced by ASLP@NPU.☆389Updated this week
- Chinese Mandarin Grapheme-to-Phoneme Converter. 中文轉注音或拼音 (INTERSPEECH 2022)☆360Updated 2 months ago
- MooER: Moore-threads Open Omni model for speech-to-speech intERaction. MooER-omni includes a series of end-to-end speech interaction mode…☆217Updated 7 months 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…☆535Updated 2 years ago
- 中文标点符号模型，可以给文本添加标点符号。☆143Updated 8 months ago
- Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training wit…☆296Updated 3 months ago
- Pseudo Streaming SenseVoice with Hotwords☆343Updated 5 months ago
- 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。☆686Updated 5 years ago
- A book about Text-to-Speech (TTS) in Chinese.☆608Updated 3 years ago
- FunCodec is a research-oriented toolkit for audio quantization and downstream applications, such as text-to-speech synthesis, music gener…☆424Updated last year
- Dolphin is a multilingual, multitask ASR model jointly trained by DataoceanAI and Tsinghua University.☆605Updated last month
- Pronunciation lexicon covering both English and Chinese languages for Automatic Speech Recognition.☆260Updated 5 years ago
- 📣 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 …☆575Updated last year
- ☆201Updated 11 months 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 …☆480Updated 3 years ago
- Fine-tune the Whisper speech recognition model to support training without timestamp data, training with timestamp data, and training wit…☆1,117Updated 2 months ago
- Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SOTA on public Mandarin ASR be…☆1,285Updated 5 months ago
- Unoffical implementation of Megatts2☆286Updated last year
- Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice☆388Updated last month