vumichien's picture
Update config.json
e85a25d
{
"_name_or_path": "vumichien/nonsemantic-speech-trillsson3",
"architectures": [
"Trillsson_efficientForSequenceClassification"
],
"classifier_dropout_prob": 0.8,
"depth_divisible_by": 8,
"depth_multiplier": 1.0,
"drop_connect_rate": 0.2,
"expand_ratio": 6,
"f_max": 7500.0,
"f_min": 125.0,
"fft_length": null,
"finetuning_task": "audio-classification",
"hidden_act": "swish",
"hop_length_secs": 0.01,
"id2label": {
"0": "yes",
"1": "no",
"10": "_silence_",
"11": "_unknown_",
"2": "up",
"3": "down",
"4": "left",
"5": "right",
"6": "on",
"7": "off",
"8": "stop",
"9": "go"
},
"initializer_range": 0.02,
"label2id": {
"_silence_": 10,
"_unknown_": 11,
"down": 3,
"go": 9,
"left": 4,
"no": 1,
"off": 7,
"on": 6,
"right": 5,
"stop": 8,
"up": 2,
"yes": 0
},
"log_additive_offset": 0.001,
"log_floor": 1e-12,
"min_depth": 8,
"model_type": "trillsson_efficient",
"norm_eps": 0.001,
"norm_momentum": 0.1,
"num_channels": 3,
"output_size": 1024,
"output_stride": 32,
"problem_type": "single_label_classification",
"tf_padding": true,
"torch_dtype": "float32",
"transformers_version": "4.23.0.dev0",
"window_length_secs": 0.025
}