Uploading model checkpoint
Browse files- config.json +99 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +11 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/w2v-bert-2.0",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_act": "relu",
|
| 5 |
+
"adapter_kernel_size": 3,
|
| 6 |
+
"adapter_stride": 2,
|
| 7 |
+
"add_adapter": false,
|
| 8 |
+
"apply_spec_augment": false,
|
| 9 |
+
"architectures": [
|
| 10 |
+
"Wav2Vec2BertForSequenceClassification"
|
| 11 |
+
],
|
| 12 |
+
"attention_dropout": 0.0,
|
| 13 |
+
"bos_token_id": 1,
|
| 14 |
+
"classifier_proj_size": 768,
|
| 15 |
+
"codevector_dim": 768,
|
| 16 |
+
"conformer_conv_dropout": 0.1,
|
| 17 |
+
"contrastive_logits_temperature": 0.1,
|
| 18 |
+
"conv_depthwise_kernel_size": 31,
|
| 19 |
+
"ctc_loss_reduction": "sum",
|
| 20 |
+
"ctc_zero_infinity": false,
|
| 21 |
+
"diversity_loss_weight": 0.1,
|
| 22 |
+
"eos_token_id": 2,
|
| 23 |
+
"feat_proj_dropout": 0.0,
|
| 24 |
+
"feat_quantizer_dropout": 0.0,
|
| 25 |
+
"feature_projection_input_dim": 160,
|
| 26 |
+
"final_dropout": 0.1,
|
| 27 |
+
"finetuning_task": "audio-classification",
|
| 28 |
+
"hidden_act": "swish",
|
| 29 |
+
"hidden_dropout": 0.0,
|
| 30 |
+
"hidden_size": 1024,
|
| 31 |
+
"id2label": {
|
| 32 |
+
"0": "Gyeongsang-do",
|
| 33 |
+
"1": "Jeolla-do",
|
| 34 |
+
"2": "Chungcheong-do",
|
| 35 |
+
"3": "Jeju-do",
|
| 36 |
+
"4": "Gangwon-do",
|
| 37 |
+
"5": "Seoul/Gyeonggi-do"
|
| 38 |
+
},
|
| 39 |
+
"initializer_range": 0.02,
|
| 40 |
+
"intermediate_size": 4096,
|
| 41 |
+
"label2id": {
|
| 42 |
+
"Chungcheong-do": "2",
|
| 43 |
+
"Gangwon-do": "4",
|
| 44 |
+
"Gyeongsang-do": "0",
|
| 45 |
+
"Jeju-do": "3",
|
| 46 |
+
"Jeolla-do": "1",
|
| 47 |
+
"Seoul/Gyeonggi-do": "5"
|
| 48 |
+
},
|
| 49 |
+
"layer_norm_eps": 1e-05,
|
| 50 |
+
"layerdrop": 0.1,
|
| 51 |
+
"left_max_position_embeddings": 64,
|
| 52 |
+
"mask_feature_length": 10,
|
| 53 |
+
"mask_feature_min_masks": 0,
|
| 54 |
+
"mask_feature_prob": 0.0,
|
| 55 |
+
"mask_time_length": 10,
|
| 56 |
+
"mask_time_min_masks": 2,
|
| 57 |
+
"mask_time_prob": 0.05,
|
| 58 |
+
"max_source_positions": 5000,
|
| 59 |
+
"model_type": "wav2vec2-bert",
|
| 60 |
+
"num_adapter_layers": 1,
|
| 61 |
+
"num_attention_heads": 16,
|
| 62 |
+
"num_codevector_groups": 2,
|
| 63 |
+
"num_codevectors_per_group": 320,
|
| 64 |
+
"num_hidden_layers": 24,
|
| 65 |
+
"num_negatives": 100,
|
| 66 |
+
"output_hidden_size": 1024,
|
| 67 |
+
"pad_token_id": 0,
|
| 68 |
+
"position_embeddings_type": "relative_key",
|
| 69 |
+
"proj_codevector_dim": 768,
|
| 70 |
+
"right_max_position_embeddings": 8,
|
| 71 |
+
"rotary_embedding_base": 10000,
|
| 72 |
+
"tdnn_dilation": [
|
| 73 |
+
1,
|
| 74 |
+
2,
|
| 75 |
+
3,
|
| 76 |
+
1,
|
| 77 |
+
1
|
| 78 |
+
],
|
| 79 |
+
"tdnn_dim": [
|
| 80 |
+
512,
|
| 81 |
+
512,
|
| 82 |
+
512,
|
| 83 |
+
512,
|
| 84 |
+
1500
|
| 85 |
+
],
|
| 86 |
+
"tdnn_kernel": [
|
| 87 |
+
5,
|
| 88 |
+
3,
|
| 89 |
+
3,
|
| 90 |
+
1,
|
| 91 |
+
1
|
| 92 |
+
],
|
| 93 |
+
"torch_dtype": "float32",
|
| 94 |
+
"transformers_version": "4.47.1",
|
| 95 |
+
"use_intermediate_ffn_before_adapter": false,
|
| 96 |
+
"use_weighted_layer_sum": false,
|
| 97 |
+
"vocab_size": null,
|
| 98 |
+
"xvector_output_dim": 512
|
| 99 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57eac7322298924004ef6a4caf0092ddbd163ffb8c16c8fdb39bc13aea0251f7
|
| 3 |
+
size 2325242152
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7916696f94e778b41f230cac6c6da10cb5bd34bdd908f6d3e96e7ac4004e3d57
|
| 3 |
+
size 6338834
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"feature_extractor_type": "SeamlessM4TFeatureExtractor",
|
| 3 |
+
"feature_size": 80,
|
| 4 |
+
"num_mel_bins": 80,
|
| 5 |
+
"padding_side": "right",
|
| 6 |
+
"padding_value": 1,
|
| 7 |
+
"processor_class": "Wav2Vec2BertProcessor",
|
| 8 |
+
"return_attention_mask": false,
|
| 9 |
+
"sampling_rate": 16000,
|
| 10 |
+
"stride": 2
|
| 11 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:425c838a5f0d570123d782a158a53b871eaaada67e2fe5ed41d669a48fda312a
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21837a51374d017bf0bf7997b61f5ced030d5d154bfdcc8254a3a4ef7ef9e1be
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7a0d443d482a8e38df75c35a92e79c1eaa7306176580c90d8655f94b68492067
|
| 3 |
+
size 5368
|