wenet-e2e / wesubtitle
用 OCR 提取视频硬字幕
☆58Updated last year
Related projects ⓘ
Alternatives and complementary repositories for wesubtitle
- SenseVoice-python: A enterprise-grade open source multi-language asr system from funasr opensource with onnxruntime☆72Updated last month
- A enterprise-grade Voice Activity Detector from modelscope and funasr.☆59Updated last year
- paraformer(chinense asr) online onnx runtime for python☆35Updated 7 months ago
- Pseudo Streaming SenseVoice with Hotwords☆73Updated last week
- Grapheme-to-Phoneme lexicons for Chinese dialects☆66Updated last year
- TTS appalication based on modelscope KAN-TTS☆43Updated 6 months ago
- ☆36Updated 3 months ago
- Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English☆71Updated this week
- Bert-VITS2 onnx推理版本☆40Updated 6 months ago
- ASR 2Pass onnxruntime and websocket server, based on FunASR(https://github.com/alibaba-damo-academy/FunASR).☆52Updated 2 months ago
- 基于 g2pW 提升 pypinyin 的准确性☆78Updated last year
- 端到端语音唤醒工具箱，从模型训练到模型推理。☆73Updated 2 months ago
- Huawei Grad-TTS for Chinese☆45Updated last year
- paraformer web server build with sanic☆19Updated last year
- ☆80Updated last year
- 基于PyTorch的VITS-BigVGAN的tts中文模型，加入韵律预测模型。☆193Updated 2 years ago
- A enterprise-grade Chinese-English code switch punctuator from funasr.☆17Updated 6 months ago
- 修复funasr中seaco-paraformer导出onnx后没有时间戳的bug☆14Updated last month
- 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
- flow mirror models from JZX AI Labs☆40Updated last month
- 中文标点符号模型，可以给文本添加标点符号。☆130Updated 8 months ago
- Production First and Production Ready End-to-End Text-to-Speech Toolkit☆371Updated 5 months ago
- ☆29Updated 5 years ago
- We Speech Transcript based on LLM, in 300 lines of code.☆126Updated 2 months ago
- Bert-VITS2项目bug多且教程不友好。本proj尽可能修复了Bert-vits2项目的bug，并且可一键启动训练。仅需50条目标说话人语音，获得稳定、快速的TTS模型。☆28Updated last month
- ☆65Updated last year
- VITS2 for Chinese speech | 最新VITS2中文语音合成☆126Updated last year