Commit
•
356d360
1
Parent(s):
f946537
update to pretraining
Browse files- config.json +10 -2
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -2,10 +2,12 @@
|
|
| 2 |
"activation_dropout": 0.0,
|
| 3 |
"apply_spec_augment": true,
|
| 4 |
"architectures": [
|
| 5 |
-
"
|
| 6 |
],
|
| 7 |
"attention_dropout": 0.1,
|
| 8 |
"bos_token_id": 1,
|
|
|
|
|
|
|
| 9 |
"conv_bias": true,
|
| 10 |
"conv_dim": [
|
| 11 |
512,
|
|
@@ -36,12 +38,14 @@
|
|
| 36 |
],
|
| 37 |
"ctc_loss_reduction": "sum",
|
| 38 |
"ctc_zero_infinity": false,
|
|
|
|
| 39 |
"do_stable_layer_norm": true,
|
| 40 |
"eos_token_id": 2,
|
| 41 |
"feat_extract_activation": "gelu",
|
| 42 |
"feat_extract_dropout": 0.0,
|
| 43 |
"feat_extract_norm": "layer",
|
| 44 |
"feat_proj_dropout": 0.1,
|
|
|
|
| 45 |
"final_dropout": 0.0,
|
| 46 |
"gradient_checkpointing": false,
|
| 47 |
"hidden_act": "gelu",
|
|
@@ -65,11 +69,15 @@
|
|
| 65 |
"mask_time_selection": "static",
|
| 66 |
"model_type": "wav2vec2",
|
| 67 |
"num_attention_heads": 16,
|
|
|
|
|
|
|
| 68 |
"num_conv_pos_embedding_groups": 16,
|
| 69 |
"num_conv_pos_embeddings": 128,
|
| 70 |
"num_feat_extract_layers": 7,
|
| 71 |
"num_hidden_layers": 24,
|
|
|
|
| 72 |
"pad_token_id": 0,
|
| 73 |
-
"
|
|
|
|
| 74 |
"vocab_size": 32
|
| 75 |
}
|
| 2 |
"activation_dropout": 0.0,
|
| 3 |
"apply_spec_augment": true,
|
| 4 |
"architectures": [
|
| 5 |
+
"Wav2Vec2ForPreTraining"
|
| 6 |
],
|
| 7 |
"attention_dropout": 0.1,
|
| 8 |
"bos_token_id": 1,
|
| 9 |
+
"codevector_dim": 768,
|
| 10 |
+
"contrastive_logits_temperature": 0.1,
|
| 11 |
"conv_bias": true,
|
| 12 |
"conv_dim": [
|
| 13 |
512,
|
| 38 |
],
|
| 39 |
"ctc_loss_reduction": "sum",
|
| 40 |
"ctc_zero_infinity": false,
|
| 41 |
+
"diversity_loss_weight": 0.1,
|
| 42 |
"do_stable_layer_norm": true,
|
| 43 |
"eos_token_id": 2,
|
| 44 |
"feat_extract_activation": "gelu",
|
| 45 |
"feat_extract_dropout": 0.0,
|
| 46 |
"feat_extract_norm": "layer",
|
| 47 |
"feat_proj_dropout": 0.1,
|
| 48 |
+
"feat_quantizer_dropout": 0.0,
|
| 49 |
"final_dropout": 0.0,
|
| 50 |
"gradient_checkpointing": false,
|
| 51 |
"hidden_act": "gelu",
|
| 69 |
"mask_time_selection": "static",
|
| 70 |
"model_type": "wav2vec2",
|
| 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 |
"pad_token_id": 0,
|
| 80 |
+
"proj_codevector_dim": 768,
|
| 81 |
+
"transformers_version": "4.7.0.dev0",
|
| 82 |
"vocab_size": 32
|
| 83 |
}
|
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:aec990077491d3c740eef7b2ed9da4568cf47f505343e1122a36da4b75bc4bc6
|
| 3 |
+
size 1269737156
|