Training in progress, step 5000
Browse files
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "facebook/wav2vec2-
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_attn_dim": null,
|
5 |
"adapter_kernel_size": 3,
|
@@ -9,7 +9,7 @@
|
|
9 |
"architectures": [
|
10 |
"Wav2Vec2ForCTC"
|
11 |
],
|
12 |
-
"attention_dropout": 0.
|
13 |
"bos_token_id": 1,
|
14 |
"classifier_proj_size": 256,
|
15 |
"codevector_dim": 768,
|
@@ -50,31 +50,23 @@
|
|
50 |
"feat_extract_activation": "gelu",
|
51 |
"feat_extract_dropout": 0.0,
|
52 |
"feat_extract_norm": "layer",
|
53 |
-
"feat_proj_dropout": 0.
|
54 |
"feat_quantizer_dropout": 0.0,
|
55 |
"final_dropout": 0.0,
|
56 |
"gradient_checkpointing": false,
|
57 |
"hidden_act": "gelu",
|
58 |
-
"hidden_dropout": 0.
|
59 |
"hidden_size": 1024,
|
60 |
"initializer_range": 0.02,
|
61 |
"intermediate_size": 4096,
|
62 |
"layer_norm_eps": 1e-05,
|
63 |
-
"layerdrop": 0.
|
64 |
-
"mask_channel_length": 10,
|
65 |
-
"mask_channel_min_space": 1,
|
66 |
-
"mask_channel_other": 0.0,
|
67 |
-
"mask_channel_prob": 0.0,
|
68 |
-
"mask_channel_selection": "static",
|
69 |
"mask_feature_length": 10,
|
70 |
"mask_feature_min_masks": 0,
|
71 |
"mask_feature_prob": 0.0,
|
72 |
"mask_time_length": 10,
|
73 |
"mask_time_min_masks": 2,
|
74 |
-
"
|
75 |
-
"mask_time_other": 0.0,
|
76 |
-
"mask_time_prob": 0.075,
|
77 |
-
"mask_time_selection": "static",
|
78 |
"model_type": "wav2vec2",
|
79 |
"num_adapter_layers": 3,
|
80 |
"num_attention_heads": 16,
|
|
|
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,
|
|
|
9 |
"architectures": [
|
10 |
"Wav2Vec2ForCTC"
|
11 |
],
|
12 |
+
"attention_dropout": 0.0,
|
13 |
"bos_token_id": 1,
|
14 |
"classifier_proj_size": 256,
|
15 |
"codevector_dim": 768,
|
|
|
50 |
"feat_extract_activation": "gelu",
|
51 |
"feat_extract_dropout": 0.0,
|
52 |
"feat_extract_norm": "layer",
|
53 |
+
"feat_proj_dropout": 0.0,
|
54 |
"feat_quantizer_dropout": 0.0,
|
55 |
"final_dropout": 0.0,
|
56 |
"gradient_checkpointing": false,
|
57 |
"hidden_act": "gelu",
|
58 |
+
"hidden_dropout": 0.0,
|
59 |
"hidden_size": 1024,
|
60 |
"initializer_range": 0.02,
|
61 |
"intermediate_size": 4096,
|
62 |
"layer_norm_eps": 1e-05,
|
63 |
+
"layerdrop": 0.0,
|
|
|
|
|
|
|
|
|
|
|
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": 0.05,
|
|
|
|
|
|
|
70 |
"model_type": "wav2vec2",
|
71 |
"num_adapter_layers": 3,
|
72 |
"num_attention_heads": 16,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262065837
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43472e24d189b2f44d578c9bbe13934e482d542ed83cc8690c38a342cd4360cd
|
3 |
size 1262065837
|
runs/Aug02_07-42-47_d8a8fd33721f/events.out.tfevents.1690962833.d8a8fd33721f.2058.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40b79a9dc5163205fa3c925e81444917591754e0983c77b15a6b93f941bcde0f
|
3 |
+
size 13468
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3963
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77c7494bf305351a33e1eb042566becde984e65278bfce31e4f7217869a509d5
|
3 |
size 3963
|