End of training
Browse files
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "facebook/wav2vec2-
|
| 3 |
"activation_dropout": 0.1,
|
| 4 |
"adapter_kernel_size": 3,
|
| 5 |
"adapter_stride": 2,
|
|
@@ -13,7 +13,7 @@
|
|
| 13 |
"classifier_proj_size": 256,
|
| 14 |
"codevector_dim": 256,
|
| 15 |
"contrastive_logits_temperature": 0.1,
|
| 16 |
-
"conv_bias":
|
| 17 |
"conv_dim": [
|
| 18 |
512,
|
| 19 |
512,
|
|
@@ -44,20 +44,20 @@
|
|
| 44 |
"ctc_loss_reduction": "mean",
|
| 45 |
"ctc_zero_infinity": false,
|
| 46 |
"diversity_loss_weight": 0.1,
|
| 47 |
-
"do_stable_layer_norm":
|
| 48 |
"eos_token_id": 2,
|
| 49 |
"feat_extract_activation": "gelu",
|
| 50 |
"feat_extract_dropout": 0.0,
|
| 51 |
-
"feat_extract_norm": "
|
| 52 |
"feat_proj_dropout": 0.0,
|
| 53 |
"feat_quantizer_dropout": 0.0,
|
| 54 |
"final_dropout": 0.1,
|
| 55 |
"hidden_act": "gelu",
|
| 56 |
"hidden_dropout": 0.05,
|
| 57 |
"hidden_dropout_prob": 0.1,
|
| 58 |
-
"hidden_size":
|
| 59 |
"initializer_range": 0.02,
|
| 60 |
-
"intermediate_size":
|
| 61 |
"layer_norm_eps": 1e-05,
|
| 62 |
"layerdrop": 0.045,
|
| 63 |
"mask_feature_length": 10,
|
|
@@ -68,15 +68,15 @@
|
|
| 68 |
"mask_time_prob": 0.05,
|
| 69 |
"model_type": "wav2vec2",
|
| 70 |
"num_adapter_layers": 3,
|
| 71 |
-
"num_attention_heads":
|
| 72 |
"num_codevector_groups": 2,
|
| 73 |
"num_codevectors_per_group": 320,
|
| 74 |
"num_conv_pos_embedding_groups": 16,
|
| 75 |
"num_conv_pos_embeddings": 128,
|
| 76 |
"num_feat_extract_layers": 7,
|
| 77 |
-
"num_hidden_layers":
|
| 78 |
"num_negatives": 100,
|
| 79 |
-
"output_hidden_size":
|
| 80 |
"pad_token_id": 23,
|
| 81 |
"proj_codevector_dim": 256,
|
| 82 |
"tdnn_dilation": [
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "facebook/wav2vec2-large-960h-lv60-self",
|
| 3 |
"activation_dropout": 0.1,
|
| 4 |
"adapter_kernel_size": 3,
|
| 5 |
"adapter_stride": 2,
|
|
|
|
| 13 |
"classifier_proj_size": 256,
|
| 14 |
"codevector_dim": 256,
|
| 15 |
"contrastive_logits_temperature": 0.1,
|
| 16 |
+
"conv_bias": true,
|
| 17 |
"conv_dim": [
|
| 18 |
512,
|
| 19 |
512,
|
|
|
|
| 44 |
"ctc_loss_reduction": "mean",
|
| 45 |
"ctc_zero_infinity": false,
|
| 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": 0.0,
|
| 53 |
"feat_quantizer_dropout": 0.0,
|
| 54 |
"final_dropout": 0.1,
|
| 55 |
"hidden_act": "gelu",
|
| 56 |
"hidden_dropout": 0.05,
|
| 57 |
"hidden_dropout_prob": 0.1,
|
| 58 |
+
"hidden_size": 1024,
|
| 59 |
"initializer_range": 0.02,
|
| 60 |
+
"intermediate_size": 4096,
|
| 61 |
"layer_norm_eps": 1e-05,
|
| 62 |
"layerdrop": 0.045,
|
| 63 |
"mask_feature_length": 10,
|
|
|
|
| 68 |
"mask_time_prob": 0.05,
|
| 69 |
"model_type": "wav2vec2",
|
| 70 |
"num_adapter_layers": 3,
|
| 71 |
+
"num_attention_heads": 16,
|
| 72 |
"num_codevector_groups": 2,
|
| 73 |
"num_codevectors_per_group": 320,
|
| 74 |
"num_conv_pos_embedding_groups": 16,
|
| 75 |
"num_conv_pos_embeddings": 128,
|
| 76 |
"num_feat_extract_layers": 7,
|
| 77 |
+
"num_hidden_layers": 24,
|
| 78 |
"num_negatives": 100,
|
| 79 |
+
"output_hidden_size": 1024,
|
| 80 |
"pad_token_id": 23,
|
| 81 |
"proj_codevector_dim": 256,
|
| 82 |
"tdnn_dilation": [
|
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:f81790ec4fdab85c9d120783b8353a10bab8254305aa55d1406cac9f0c08f37d
|
| 3 |
+
size 1262027821
|
runs/Feb12_19-39-37_ccf45f913946/1676230796.5793962/events.out.tfevents.1676230796.ccf45f913946.545.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f330950c708f5394c051c934ce2fff6232cf987381429b67c3a8b3eab8e4cc88
|
| 3 |
+
size 4762
|
runs/Feb12_19-39-37_ccf45f913946/events.out.tfevents.1676230796.ccf45f913946.545.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b817ca3e8f15d23c64958dc1926dd6748b56daf67e82cb3e8558c4bcf7103a4
|
| 3 |
+
size 5998
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3003
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89a32d89deb53b13eb1fd446f916299c978d0785351050be1a0791b921374443
|
| 3 |
size 3003
|