WavCochCausalV8192-vocoder-randinit

WavCoch is a causal waveform-to-cochleagram tokenizer by Greta Tuckute and Klemen Kotar.

This repository contains a freshly initialized WavCochV8192CausalConfig model with a bundled random-initialized vocoder. The weights are random and have not been trained from a checkpoint.

Model Details

Parameter	Value
Parameters	~24.42M
Window Size	1001
Hop Length	80
Encoder Dim	512
Vocabulary Size	8192
Includes Vocoder	True

Usage

from transformers import AutoModel

wavcoch = AutoModel.from_pretrained(
    "TuKoResearch/WavCochCausalV8192-vocoder-randinit",
    trust_remote_code=True,
)

codes = wavcoch.quantize(waveform_tensor)
coch = wavcoch.decode(codes)

audio = wavcoch.decode_audio(codes)

Notes

This repo includes a bundled vocoder and supports decode_audio(...) for end-to-end waveform synthesis.