Add new voice model "Doubao" to MoYoYo configuration
liumaolin
7b003c4
- Include model details, inference parameters, and related files.
- Add reference audio and pretrained weights for TTS.
Add new voice model "Ellen" to MoYoYo configuration
liumaolin
b5b48f0
- Include model details, inference parameters, and related files.
- Add reference audio and pretrained weights for TTS.
Update reference audio for MoYoYo TTS model
liumaolin
68663d9
Add new voice model "Juniper" to MoYoYo configuration
liumaolin
469433f
- Include model details, inference parameters, and related files.
- Add reference audio and pretrained weights for TTS.
Add Maple and Cove voice models to MoYoYo TTS configuration
liumaolin
7e92ad3
- Introduce two new voice models: Maple (轻松坦率) and Cove (沉稳直率).
- Configure model repositories, parameters, and corresponding inference settings.
- Add associated model files, including GPT weights, SoVITS weights, and reference audios.
Update LLM response generator and system prompts
liumaolin
6f77a29
- Add "/no_think" directive to English and Chinese system prompts.
- Handle `<think>` and `</think>` tags in response chunk processing.
- Update LLM model file to `Qwen3-8B-Q6_K.gguf`.
- Adjust model parameters: increase context length, modify temperature, top_p, and top_k, and include `presence_penalty`.
Replace `ffmpeg`-based audio loading with `soundfile` and `librosa`
liumaolin
b6d76bc
- Switch `load_audio` implementation to use `soundfile` and `librosa` for improved compatibility and removal of `ffmpeg` dependency.
- Update index.html title to "Voice Dialogue".
- Standardize spacing in `electron-app/utils.js` and adjust file path for `.version.json`.
[fix]: update web.
Xin Zhang
5f9e92a
Update app title in index.html to "Voice Dialogue"
liumaolin
a09c130
Remove deprecated `whisper/ggml-large-v3-turbo-encoder` model files and metadata
