view post Post 3683 ๐คฏ ๐คฏ Released a high quality finetuned LLM based TTS model that can generate realistic and clear 48khz audio at over 100x realtime speed! ๐คฏ ๐คฏGithub 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 ยท ๐ฅ 10 10 ๐ 6 6 ๐ 3 3 + Reply
view post Post 2836 I just released LayaCodec, a highly efficient neural audio tokenizer/codec for TTS models, far better than most previous audio tokenizers.๐คฏ Next-gen TTS models that use this could achieve several 100s of times real-time speed while producing clearer audio!! ๐คฏGitHub repo: https://github.com/ysharma3501/LayaCodecModel: YatharthS/LayaCodec See translation ๐ฅ 6 6 ๐ 3 3 + Reply