Training in progress, epoch 0
Browse files- .gitignore +1 -0
- config.json +128 -0
- preprocessor_config.json +9 -0
- pytorch_model.bin +3 -0
- runs/Oct27_22-57-26_anton-gpu-v100/1635375474.205754/events.out.tfevents.1635375474.anton-gpu-v100.304115.1 +3 -0
- runs/Oct27_22-57-26_anton-gpu-v100/events.out.tfevents.1635375474.anton-gpu-v100.304115.0 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,128 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "asapp/sew-d-mid-400k",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"apply_spec_augment": true,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"SEWDForSequenceClassification"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.1,
|
| 9 |
+
"bos_token_id": 1,
|
| 10 |
+
"classifier_proj_size": 256,
|
| 11 |
+
"conv_bias": false,
|
| 12 |
+
"conv_dim": [
|
| 13 |
+
64,
|
| 14 |
+
128,
|
| 15 |
+
128,
|
| 16 |
+
128,
|
| 17 |
+
128,
|
| 18 |
+
256,
|
| 19 |
+
256,
|
| 20 |
+
256,
|
| 21 |
+
256,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512,
|
| 25 |
+
512
|
| 26 |
+
],
|
| 27 |
+
"conv_kernel": [
|
| 28 |
+
10,
|
| 29 |
+
3,
|
| 30 |
+
1,
|
| 31 |
+
3,
|
| 32 |
+
1,
|
| 33 |
+
3,
|
| 34 |
+
1,
|
| 35 |
+
3,
|
| 36 |
+
1,
|
| 37 |
+
2,
|
| 38 |
+
1,
|
| 39 |
+
2,
|
| 40 |
+
1
|
| 41 |
+
],
|
| 42 |
+
"conv_stride": [
|
| 43 |
+
5,
|
| 44 |
+
2,
|
| 45 |
+
1,
|
| 46 |
+
2,
|
| 47 |
+
1,
|
| 48 |
+
2,
|
| 49 |
+
1,
|
| 50 |
+
2,
|
| 51 |
+
1,
|
| 52 |
+
2,
|
| 53 |
+
1,
|
| 54 |
+
2,
|
| 55 |
+
1
|
| 56 |
+
],
|
| 57 |
+
"ctc_loss_reduction": "sum",
|
| 58 |
+
"ctc_zero_infinity": false,
|
| 59 |
+
"eos_token_id": 2,
|
| 60 |
+
"feat_extract_activation": "gelu",
|
| 61 |
+
"feat_extract_norm": "group",
|
| 62 |
+
"feat_proj_dropout": 0.1,
|
| 63 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
| 64 |
+
"final_dropout": 0.0,
|
| 65 |
+
"finetuning_task": "audio-classification",
|
| 66 |
+
"hidden_act": "gelu",
|
| 67 |
+
"hidden_dropout": 0.0,
|
| 68 |
+
"hidden_size": 512,
|
| 69 |
+
"id2label": {
|
| 70 |
+
"0": "yes",
|
| 71 |
+
"1": "no",
|
| 72 |
+
"10": "_silence_",
|
| 73 |
+
"11": "_unknown_",
|
| 74 |
+
"2": "up",
|
| 75 |
+
"3": "down",
|
| 76 |
+
"4": "left",
|
| 77 |
+
"5": "right",
|
| 78 |
+
"6": "on",
|
| 79 |
+
"7": "off",
|
| 80 |
+
"8": "stop",
|
| 81 |
+
"9": "go"
|
| 82 |
+
},
|
| 83 |
+
"initializer_range": 0.02,
|
| 84 |
+
"intermediate_size": 2048,
|
| 85 |
+
"label2id": {
|
| 86 |
+
"_silence_": "10",
|
| 87 |
+
"_unknown_": "11",
|
| 88 |
+
"down": "3",
|
| 89 |
+
"go": "9",
|
| 90 |
+
"left": "4",
|
| 91 |
+
"no": "1",
|
| 92 |
+
"off": "7",
|
| 93 |
+
"on": "6",
|
| 94 |
+
"right": "5",
|
| 95 |
+
"stop": "8",
|
| 96 |
+
"up": "2",
|
| 97 |
+
"yes": "0"
|
| 98 |
+
},
|
| 99 |
+
"layer_norm_eps": 1e-05,
|
| 100 |
+
"layerdrop": 0.2,
|
| 101 |
+
"mask_feature_length": 10,
|
| 102 |
+
"mask_feature_prob": 0.0,
|
| 103 |
+
"mask_time_length": 10,
|
| 104 |
+
"mask_time_prob": 0.65,
|
| 105 |
+
"max_position_embeddings": 512,
|
| 106 |
+
"model_type": "sew-d",
|
| 107 |
+
"norm_rel_ebd": "layer_norm",
|
| 108 |
+
"num_attention_heads": 8,
|
| 109 |
+
"num_conv_pos_embedding_groups": 16,
|
| 110 |
+
"num_conv_pos_embeddings": 31,
|
| 111 |
+
"num_feat_extract_layers": 13,
|
| 112 |
+
"num_hidden_layers": 24,
|
| 113 |
+
"pad_token_id": 0,
|
| 114 |
+
"pos_att_type": [
|
| 115 |
+
"p2c",
|
| 116 |
+
"c2p"
|
| 117 |
+
],
|
| 118 |
+
"position_biased_input": false,
|
| 119 |
+
"position_buckets": 256,
|
| 120 |
+
"relative_attention": true,
|
| 121 |
+
"share_att_key": true,
|
| 122 |
+
"squeeze_factor": 2,
|
| 123 |
+
"tokenizer_class": "Wav2Vec2CTCTokenizer",
|
| 124 |
+
"torch_dtype": "float32",
|
| 125 |
+
"transformers_version": "4.12.0.dev0",
|
| 126 |
+
"use_weighted_layer_sum": false,
|
| 127 |
+
"vocab_size": 32
|
| 128 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 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 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dc3bf0cc0425a9f9ce13b90ed2c97d7ae8eddb5ee97f6a23f8399d288539514
|
| 3 |
+
size 315912517
|
runs/Oct27_22-57-26_anton-gpu-v100/1635375474.205754/events.out.tfevents.1635375474.anton-gpu-v100.304115.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ef69a5f91950c0cd36ae39ef2e7dd18e1dc97e5be36ca8ae2bc0c73a5ac0e1e
|
| 3 |
+
size 4587
|
runs/Oct27_22-57-26_anton-gpu-v100/events.out.tfevents.1635375474.anton-gpu-v100.304115.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:218ecac93050f9a9c3b0608dbcb65177957db2cf08ca10b5d941eb1da2766d1b
|
| 3 |
+
size 11272
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bd21739cea7e9f49872a2bf39c115ca0eed7dc3ae0f14a0d945b7007c101aac
|
| 3 |
+
size 2927
|