Training in progress, epoch 1
Browse files- config.json +10 -9
- preprocessor_config.json +1 -0
- pytorch_model.bin +2 -2
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "facebook/wav2vec2-xls-r-300m",
|
| 3 |
"activation_dropout": 0.0,
|
|
|
|
| 4 |
"adapter_kernel_size": 3,
|
| 5 |
"adapter_stride": 2,
|
| 6 |
"add_adapter": false,
|
|
@@ -42,14 +43,14 @@
|
|
| 42 |
2
|
| 43 |
],
|
| 44 |
"ctc_loss_reduction": "mean",
|
| 45 |
-
"ctc_zero_infinity":
|
| 46 |
"diversity_loss_weight": 0.1,
|
| 47 |
"do_stable_layer_norm": true,
|
| 48 |
"eos_token_id": 2,
|
| 49 |
"feat_extract_activation": "gelu",
|
| 50 |
"feat_extract_dropout": 0.0,
|
| 51 |
"feat_extract_norm": "layer",
|
| 52 |
-
"feat_proj_dropout": 0.
|
| 53 |
"feat_quantizer_dropout": 0.0,
|
| 54 |
"final_dropout": 0.0,
|
| 55 |
"gradient_checkpointing": false,
|
|
@@ -59,13 +60,13 @@
|
|
| 59 |
"initializer_range": 0.02,
|
| 60 |
"intermediate_size": 4096,
|
| 61 |
"layer_norm_eps": 1e-05,
|
| 62 |
-
"layerdrop": 0.
|
| 63 |
-
"mask_feature_length":
|
| 64 |
"mask_feature_min_masks": 0,
|
| 65 |
-
"mask_feature_prob": 0.
|
| 66 |
"mask_time_length": 10,
|
| 67 |
"mask_time_min_masks": 2,
|
| 68 |
-
"mask_time_prob": 0.
|
| 69 |
"model_type": "wav2vec2",
|
| 70 |
"num_adapter_layers": 3,
|
| 71 |
"num_attention_heads": 16,
|
|
@@ -77,7 +78,7 @@
|
|
| 77 |
"num_hidden_layers": 24,
|
| 78 |
"num_negatives": 100,
|
| 79 |
"output_hidden_size": 1024,
|
| 80 |
-
"pad_token_id":
|
| 81 |
"proj_codevector_dim": 768,
|
| 82 |
"tdnn_dilation": [
|
| 83 |
1,
|
|
@@ -101,8 +102,8 @@
|
|
| 101 |
1
|
| 102 |
],
|
| 103 |
"torch_dtype": "float32",
|
| 104 |
-
"transformers_version": "4.
|
| 105 |
"use_weighted_layer_sum": false,
|
| 106 |
-
"vocab_size":
|
| 107 |
"xvector_output_dim": 512
|
| 108 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_name_or_path": "facebook/wav2vec2-xls-r-300m",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
+
"adapter_attn_dim": null,
|
| 5 |
"adapter_kernel_size": 3,
|
| 6 |
"adapter_stride": 2,
|
| 7 |
"add_adapter": false,
|
|
|
|
| 43 |
2
|
| 44 |
],
|
| 45 |
"ctc_loss_reduction": "mean",
|
| 46 |
+
"ctc_zero_infinity": true,
|
| 47 |
"diversity_loss_weight": 0.1,
|
| 48 |
"do_stable_layer_norm": true,
|
| 49 |
"eos_token_id": 2,
|
| 50 |
"feat_extract_activation": "gelu",
|
| 51 |
"feat_extract_dropout": 0.0,
|
| 52 |
"feat_extract_norm": "layer",
|
| 53 |
+
"feat_proj_dropout": 0.1,
|
| 54 |
"feat_quantizer_dropout": 0.0,
|
| 55 |
"final_dropout": 0.0,
|
| 56 |
"gradient_checkpointing": false,
|
|
|
|
| 60 |
"initializer_range": 0.02,
|
| 61 |
"intermediate_size": 4096,
|
| 62 |
"layer_norm_eps": 1e-05,
|
| 63 |
+
"layerdrop": 0.1,
|
| 64 |
+
"mask_feature_length": 10,
|
| 65 |
"mask_feature_min_masks": 0,
|
| 66 |
+
"mask_feature_prob": 0.0,
|
| 67 |
"mask_time_length": 10,
|
| 68 |
"mask_time_min_masks": 2,
|
| 69 |
+
"mask_time_prob": 0.075,
|
| 70 |
"model_type": "wav2vec2",
|
| 71 |
"num_adapter_layers": 3,
|
| 72 |
"num_attention_heads": 16,
|
|
|
|
| 78 |
"num_hidden_layers": 24,
|
| 79 |
"num_negatives": 100,
|
| 80 |
"output_hidden_size": 1024,
|
| 81 |
+
"pad_token_id": 34,
|
| 82 |
"proj_codevector_dim": 768,
|
| 83 |
"tdnn_dilation": [
|
| 84 |
1,
|
|
|
|
| 102 |
1
|
| 103 |
],
|
| 104 |
"torch_dtype": "float32",
|
| 105 |
+
"transformers_version": "4.32.1",
|
| 106 |
"use_weighted_layer_sum": false,
|
| 107 |
+
"vocab_size": 37,
|
| 108 |
"xvector_output_dim": 512
|
| 109 |
}
|
preprocessor_config.json
CHANGED
|
@@ -4,6 +4,7 @@
|
|
| 4 |
"feature_size": 1,
|
| 5 |
"padding_side": "right",
|
| 6 |
"padding_value": 0.0,
|
|
|
|
| 7 |
"return_attention_mask": true,
|
| 8 |
"sampling_rate": 16000
|
| 9 |
}
|
|
|
|
| 4 |
"feature_size": 1,
|
| 5 |
"padding_side": "right",
|
| 6 |
"padding_value": 0.0,
|
| 7 |
+
"processor_class": "Wav2Vec2Processor",
|
| 8 |
"return_attention_mask": true,
|
| 9 |
"sampling_rate": 16000
|
| 10 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:525c0a275ecc16756f13782d9fb282ab3b372f0073875b83d4540066dc2c7f8c
|
| 3 |
+
size 1262053549
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d600e3b8cf20c205223bc826c7df2a81972e29720cd9027a2a8f95dc3901407
|
| 3 |
+
size 4091
|