HydroRoll-Team / HydroRoll Star 7 Code Issues Pull requests 跨平台、多模态、高度自定义的骰系开发框架 | “如何更好的为冷门规则书做适配”?| “如何更好的实现人机交互?” nlp dice text-to-speech framework ai cross-platform model artificial-intelligence tts webui dice-roller roll asr dice-roller-library nature-language-processing hydroroll audio-speech-recognition Updated Jun 16, 2024 Python
DevExpert0101 / SpeechDoctor Star 3 Code Issues Pull requests Analyze an audio file and count words, sentences and timestamps, filler words openai speech-to-text spectral-analysis voice-activity-detection google-colab vosk audio-speech-recognition Updated Jun 23, 2023 Jupyter Notebook
hari-huynh / viVQA-voice-assistant Star 3 Code Issues Pull requests Voice assistant using Multimodal LLMs - LLaVA-NeXT (Mistral 7B) finetuned & PhoWhisper text-to-speech lora visual-question-answering llava multimodal-large-language-models audio-speech-recognition mistral-7b Updated May 15, 2024 Python