Vocoder model - FastDiff

No support given.

Details

num_iters_per_epoch: 250
max_epoch: 1000
batch_size: 64
vocoder_conf:
    audio_channels: 1
    inner_channels: 32
    cond_channels: 80
    upsample_ratios:
    - 5
    - 5
    - 4
    - 3

Downloads last month: 5

Inference Examples

Audio-to-Audio

Inference API (serverless) has been turned off for this model.