Built with Fish Audio. Experimental native audio.cpp conversions of Fish Audio Drama 3, prepared from checkpoint revision dd64a85cd82e9521f7202610ede97b367fc83946. All packages use the same trained model architecture and checkpoint. Q2, Q3 and Q4 are mixed quantizations. Q80 stores scaled 8-bit integer weights; it is different from the FP8 representation of the original checkpoint's experts. All standalone packages retain FP16 audio tower and waveform codec weights and FP32 normalization vectors. They embed the configuration, tokenizer, codec, model contract and license, so inference does not require the original checkpoint directory. This repository distributes the four runnable quantized…
Independent publisher
Jarod MICA
Jmica
Models in Library1
Datasets in Library0
Models on Hugging Face14
Followers90
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Text to speech.
Reported licenses: other. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.