hf-transformers-bot's picture
Upload tiny models for ClvpModelForConditionalGeneration
45df758
raw
history blame
1.42 kB
{
"chunk_length": 30,
"default_audio_length": 6,
"feature_extractor_type": "ClvpFeatureExtractor",
"feature_size": 80,
"hop_length": 256,
"mel_norms": [
-7.0095,
-6.0832,
-4.644,
-3.3562,
-2.4548,
-2.0097,
-1.6036,
-1.8641,
-2.3728,
-2.3455,
-2.5947,
-2.6695,
-2.7129,
-2.8555,
-3.0251,
-3.0889,
-3.4261,
-3.6759,
-4.078,
-4.4624,
-4.7812,
-5.0075,
-5.1284,
-5.2717,
-5.4006,
-5.4993,
-5.531,
-5.5878,
-5.6726,
-5.7016,
-5.7943,
-5.8831,
-5.9537,
-5.9989,
-6.0305,
-6.0539,
-6.0748,
-6.1163,
-6.1481,
-6.2476,
-6.3195,
-6.4457,
-6.5377,
-6.611,
-6.6481,
-6.6671,
-6.6539,
-6.6499,
-6.6794,
-6.7833,
-6.9307,
-7.0818,
-7.1894,
-7.2439,
-7.3168,
-7.3779,
-7.4491,
-7.5233,
-7.6224,
-7.7473,
-7.8994,
-8.0604,
-8.2181,
-8.3998,
-8.5556,
-8.7161,
-8.8481,
-8.9582,
-9.0371,
-9.0867,
-9.1546,
-9.2038,
-9.2334,
-9.2292,
-9.2304,
-9.268,
-9.3156,
-9.3716,
-9.4165,
-9.4822
],
"n_fft": 1024,
"n_samples": 661500,
"nb_max_frames": 2583,
"padding_side": "right",
"padding_value": 0.0,
"processor_class": "ClvpProcessor",
"return_attention_mask": false,
"sampling_rate": 22050
}