view post Post 2823 I just released LayaCodec, a highly efficient neural audio tokenizer/codec for TTS models, far better than most previous audio tokenizers.𤯠Next-gen TTS models that use this could achieve several 100s of times real-time speed while producing clearer audio!! š¤ÆGitHub repo: https://github.com/ysharma3501/LayaCodecModel: YatharthS/LayaCodec See translation š„ 6 6 š 3 3 + Reply