view post Post 3693 π€― π€― Released a high quality finetuned LLM based TTS model that can generate realistic and clear 48khz audio at over 100x realtime speed! π€― π€―Github link: https://github.com/ysharma3501/MiraTTSModel link: https://github.com/ysharma3501/MiraTTSBlog explaining llm tts models: https://huggingface.co/blog/YatharthS/llm-tts-models See translation 4 replies Β· π₯ 10 10 π 6 6 π 3 3 + Reply
view post Post 2837 I just released LayaCodec, a highly efficient neural audio tokenizer/codec for TTS models, far better than most previous audio tokenizers.π€― Next-gen TTS models that use this could achieve several 100s of times real-time speed while producing clearer audio!! π€―GitHub repo: https://github.com/ysharma3501/LayaCodecModel: YatharthS/LayaCodec See translation π₯ 6 6 π 3 3 + Reply