DakeQQ
DakeQQ
1. 欢迎使用[本仓库](https://github.com/DakeQQ/Transcribe-and-Translate-Subtitles)来离线转录和翻译视频 (支持批量)，确保最高的隐私保护。 2. 翻译功能基于大语言模型（LLM），如 Qwen2.5-7B、Qwen2.5-14B、GLM4-9B 等。 3. 该工具对于CPU用户友好，16GB 内存的电脑即可运行LLM-7B。 4. 转录功能依托于多种强大的模型，包括 SenseVoiceSmall、Paraformer、Whisper V2 / V3 / Turbo，以及针对日语的微调 Whisper 模型。 5. 仓库包含 SenseVoiceSmall、Paraformer、FSMN-VAD、Denoiser-ZipEnhancer 和 Denoiser-DFSMN，这些都是阿里巴巴家族的模型，在中文任务中表现优异。
Feel free to use this [repo](https://github.com/DakeQQ/STFT-ISTFT-ONNX) to export your custom STFT or ISTFT process to ONNX format.
Feel free to use this [repo](https://github.com/DakeQQ/STFT-ISTFT-ONNX) to export your custom STFT or ISTFT process to ONNX format. There’s no need to separate the STFT and ISTFT from the model anymore.
Feel free to reference this [repo](https://github.com/DakeQQ/Automatic-Speech-Recognition-ASR-ONNX). It is an end-to-end version that includes the STFT process. Simply provide the audio input to obtain the ASR result. You can also customize...
Feel free to reference this [repo](https://github.com/DakeQQ/Automatic-Speech-Recognition-ASR-ONNX). It is an end-to-end version that includes the STFT process. Simply provide the audio input to obtain the ASR result. You can also customize...
欢迎参考这份[Python脚本](https://github.com/DakeQQ/Native-LLM-for-Android/blob/main/Export_ONNX/MiniCPM/MiniCPM_Export.py)来导出MiniCPM4-ONNX
[欢迎参考ONNX Runtime框架的YOLO :)](https://github.com/DakeQQ/YOLO-Depth-Estimation-for-Android)
Welcome to refer to this [export script](https://github.com/DakeQQ/Text-to-Speech-TTS-ONNX/blob/main/BigVGAN/Export_BigVGAN.py) to export BigVGAN to ONNX format.
Feel free to reference this [repo](https://github.com/DakeQQ/Automatic-Speech-Recognition-ASR-ONNX). It is an end-to-end version that includes the STFT process. Simply provide the audio input to obtain the ASR result. You can also customize...
@theseriouspdx Feel free to explore this [repository](https://github.com/DakeQQ/Transcribe-and-Translate-Subtitles), designed specifically for CPU-only users. With an Intel i3-12300 CPU (4 threads), it can transcribe a 2-hour movie in approximately 20 minutes using...