Text-to-Audio
Transformers
music
text-to-music
Inference Endpoints
mustango / configs /stft_config.json
deepanway's picture
upload files
386c9b1
raw
history blame
141 Bytes
{"filter_length": 1024, "hop_length": 160, "win_length": 1024, "n_mel_channels": 64, "sampling_rate": 16000, "mel_fmin": 0, "mel_fmax": 8000}