D3-Omni-Mini / audio_encoder /preprocessor_config.json

Upload Model

252ced4 20 days ago

603 Bytes

{
  "dither": 0.0,
  "feature_extractor_type": "WhisperFeatureExtractor",
  "feature_size": 128,
  "hop_length": 160,
  "image_mean": [
    0.5,
    0.5,
    0.5
  ],
  "image_processor_type": "Qwen2VLImageProcessor",
  "image_std": [
    0.5,
    0.5,
    0.5
  ],
  "max_pixels": 12845056,
  "merge_size": 2,
  "min_pixels": 3136,
  "n_fft": 400,
  "n_samples": 4800000,
  "nb_max_frames": 30000,
  "padding_side": "right",
  "padding_value": 0.0,
  "patch_size": 16,
  "processor_class": "Qwen3OmniMoeProcessor",
  "return_attention_mask": true,
  "sampling_rate": 16000,
  "temporal_patch_size": 2
}

	{
	"dither": 0.0,
	"feature_extractor_type": "WhisperFeatureExtractor",
	"feature_size": 128,
	"hop_length": 160,
	"image_mean": [
	0.5,
	0.5,
	0.5
	],
	"image_processor_type": "Qwen2VLImageProcessor",
	"image_std": [
	0.5,
	0.5,
	0.5
	],
	"max_pixels": 12845056,
	"merge_size": 2,
	"min_pixels": 3136,
	"n_fft": 400,
	"n_samples": 4800000,
	"nb_max_frames": 30000,
	"padding_side": "right",
	"padding_value": 0.0,
	"patch_size": 16,
	"processor_class": "Qwen3OmniMoeProcessor",
	"return_attention_mask": true,
	"sampling_rate": 16000,
	"temporal_patch_size": 2
	}