metadata
license: apache-2.0
tags:
- audio
- speech
- tokenizer
- vocoder
- wavcoch
library_name: transformers
WavCochCausalV8192-vocoder
WavCoch is a causal waveform-to-cochleagram tokenizer by Greta Tuckute and Klemen Kotar.
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",
trust_remote_code=True,
)
codes = wavcoch.quantize(waveform_tensor)
coch = wavcoch.decode(codes)
embeddings = wavcoch(
input_values=waveform_tensor,
output_hidden_states=True,
sampling_rate=16000,
).hidden_states[0]
audio = wavcoch.decode_audio(codes)
Notes
This repo includes a bundled vocoder and supports decode_audio(...) for end-to-end waveform synthesis.
When called with output_hidden_states=True, WavCoch exposes a single hidden-state layer:
the post-FSQ projected embedding sequence used for direct probing.