model upload
Browse files- config.json +76 -0
- preprocessor_config.json +9 -0
config.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "utter-project/hutter-12-3rd-base",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"apply_spec_augment": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"HubertModel"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"classifier_proj_size": 256,
|
| 11 |
+
"conv_bias": false,
|
| 12 |
+
"conv_dim": [
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512,
|
| 19 |
+
512
|
| 20 |
+
],
|
| 21 |
+
"conv_kernel": [
|
| 22 |
+
10,
|
| 23 |
+
3,
|
| 24 |
+
3,
|
| 25 |
+
3,
|
| 26 |
+
3,
|
| 27 |
+
2,
|
| 28 |
+
2
|
| 29 |
+
],
|
| 30 |
+
"conv_stride": [
|
| 31 |
+
5,
|
| 32 |
+
2,
|
| 33 |
+
2,
|
| 34 |
+
2,
|
| 35 |
+
2,
|
| 36 |
+
2,
|
| 37 |
+
2
|
| 38 |
+
],
|
| 39 |
+
"ctc_loss_reduction": "sum",
|
| 40 |
+
"ctc_zero_infinity": false,
|
| 41 |
+
"do_stable_layer_norm": false,
|
| 42 |
+
"eos_token_id": 2,
|
| 43 |
+
"feat_extract_activation": "gelu",
|
| 44 |
+
"feat_extract_dropout": 0.0,
|
| 45 |
+
"feat_extract_norm": "group",
|
| 46 |
+
"feat_proj_dropout": 0.1,
|
| 47 |
+
"feat_proj_layer_norm": true,
|
| 48 |
+
"final_dropout": 0.1,
|
| 49 |
+
"gradient_checkpointing": false,
|
| 50 |
+
"hidden_act": "gelu",
|
| 51 |
+
"hidden_dropout": 0.1,
|
| 52 |
+
"hidden_dropout_prob": 0.1,
|
| 53 |
+
"hidden_size": 768,
|
| 54 |
+
"initializer_range": 0.02,
|
| 55 |
+
"intermediate_size": 3072,
|
| 56 |
+
"layer_norm_eps": 1e-05,
|
| 57 |
+
"layerdrop": 0.1,
|
| 58 |
+
"mask_feature_length": 10,
|
| 59 |
+
"mask_feature_min_masks": 0,
|
| 60 |
+
"mask_feature_prob": 0.0,
|
| 61 |
+
"mask_time_length": 10,
|
| 62 |
+
"mask_time_min_masks": 2,
|
| 63 |
+
"mask_time_prob": 0.05,
|
| 64 |
+
"model_type": "hubert",
|
| 65 |
+
"num_attention_heads": 12,
|
| 66 |
+
"num_conv_pos_embedding_groups": 16,
|
| 67 |
+
"num_conv_pos_embeddings": 128,
|
| 68 |
+
"num_feat_extract_layers": 7,
|
| 69 |
+
"num_hidden_layers": 12,
|
| 70 |
+
"pad_token_id": 0,
|
| 71 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 72 |
+
"torch_dtype": "float32",
|
| 73 |
+
"transformers_version": "4.25.0.dev0",
|
| 74 |
+
"use_weighted_layer_sum": false,
|
| 75 |
+
"vocab_size": 32
|
| 76 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": false,
|
| 3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 4 |
+
"feature_size": 1,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 0,
|
| 7 |
+
"return_attention_mask": false,
|
| 8 |
+
"sampling_rate": 16000
|
| 9 |
+
}
|