mazrba/Chatterbox-TTS-Indonesian-gguf

In the Name of God

🚨 The file has been updated and the reported crash has been fixed.

Chatterbox TTS Indonesian gguf

GGUF / ggml conversion of `grandhigh/Chatterbox-TTS-Indonesian` for use with [CrispStrobe/CrispASR](https://github.com/CrispStrobe/CrispASR).

Indonesian T3 (text-to-speech-tokens) variant of Chatterbox TTS.

demo audios:

<audio controls src="https://huggingface.co/grandhigh/Chatterbox-TTS-Indonesian/resolve/main/example1.wav">Your browser does not support audio.</audio>

<audio controls src="https://huggingface.co/grandhigh/Chatterbox-TTS-Indonesian/resolve/main/example2.wav">Your browser does not support audio.</audio>

Chatterbox is a full TTS pipeline: character tokenizer → T3 (30-layer Llama AR, 520M) → speech tokens → S3Gen (Conformer encoder + UNet1D CFM denoiser, 10 Euler steps) → HiFTGenerator vocoder (conv chains + Snake activations + iSTFT) → 24 kHz WAV.

How to use:

Two GGUF files are needed: the T3 model (text → speech tokens) and the S3Gen model (speech tokens → audio).

1. 1.Download CrispASR:

`github.com/CrispStrobe/CrispASR/releases`

1. 1.Download model files:

chatterbox-t3-id-f16.gguf

chatterbox-s3gen-q8_0.gguf

1. 1.Synthesise with the built-in default voice:

./crispasr.exe --backend chatterbox -m chatterbox-t3-id-f16.gguf --codec-model chatterbox-s3gen-q8_0.gguf --tts "Sistem ini dirancang untuk memberikan akses cepat dan mudah kepada pengguna terhadap informasi yang dibutuhkan." --tts-output out.wav