omnivoice-mlx-q4-g64 / audio_tokenizer /preprocessor_config.json

OmniVoice MLX q4-g64: Qwen3 backbone quantized via mlx-lm; Higgs tokenizer bf16

c2c7cf4 verified 6 months ago

206 Bytes

{
  "feature_extractor_type": "DacFeatureExtractor",
  "feature_size": 1,
  "hop_length": 960,
  "padding_side": "right",
  "padding_value": 0.0,
  "return_attention_mask": true,
  "sampling_rate": 24000
}

	{
	"feature_extractor_type": "DacFeatureExtractor",
	"feature_size": 1,
	"hop_length": 960,
	"padding_side": "right",
	"padding_value": 0.0,
	"return_attention_mask": true,
	"sampling_rate": 24000
	}