Training in progress, step 1600
Browse files
README.md
CHANGED
@@ -1,10 +1,4 @@
|
|
1 |
-
|
2 |
-
license: apache-2.0
|
3 |
-
tags:
|
4 |
-
- generated_from_trainer
|
5 |
-
model-index:
|
6 |
-
name: d-l-dl
|
7 |
-
---
|
8 |
|
9 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
should probably proofread and complete it, then remove this comment. -->
|
|
|
1 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
|
3 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
4 |
should probably proofread and complete it, then remove this comment. -->
|
config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"activation_dropout": 0.
|
4 |
"apply_spec_augment": true,
|
5 |
"architectures": [
|
6 |
"Wav2Vec2ForCTC"
|
@@ -8,9 +8,9 @@
|
|
8 |
"attention_dropout": 0.5,
|
9 |
"bos_token_id": 1,
|
10 |
"classifier_proj_size": 256,
|
11 |
-
"codevector_dim":
|
12 |
"contrastive_logits_temperature": 0.1,
|
13 |
-
"conv_bias":
|
14 |
"conv_dim": [
|
15 |
512,
|
16 |
512,
|
@@ -39,42 +39,48 @@
|
|
39 |
2
|
40 |
],
|
41 |
"ctc_loss_reduction": "mean",
|
42 |
-
"ctc_zero_infinity":
|
43 |
"diversity_loss_weight": 0.1,
|
44 |
-
"do_stable_layer_norm":
|
45 |
"eos_token_id": 2,
|
46 |
"feat_extract_activation": "gelu",
|
47 |
"feat_extract_dropout": 0.0,
|
48 |
-
"feat_extract_norm": "
|
49 |
"feat_proj_dropout": 0.0,
|
50 |
"feat_quantizer_dropout": 0.0,
|
51 |
-
"final_dropout": 0.
|
52 |
-
"gradient_checkpointing": false,
|
53 |
"hidden_act": "gelu",
|
54 |
"hidden_dropout": 0.0,
|
55 |
-
"
|
56 |
-
"hidden_size": 768,
|
57 |
"initializer_range": 0.02,
|
58 |
-
"intermediate_size":
|
59 |
"layer_norm_eps": 1e-05,
|
60 |
"layerdrop": 0.0,
|
|
|
|
|
|
|
|
|
|
|
61 |
"mask_feature_length": 10,
|
62 |
"mask_feature_prob": 0.0,
|
63 |
"mask_time_length": 10,
|
|
|
|
|
64 |
"mask_time_prob": 0.05,
|
|
|
65 |
"model_type": "wav2vec2",
|
66 |
-
"num_attention_heads":
|
67 |
"num_codevector_groups": 2,
|
68 |
"num_codevectors_per_group": 320,
|
69 |
"num_conv_pos_embedding_groups": 16,
|
70 |
"num_conv_pos_embeddings": 128,
|
71 |
"num_feat_extract_layers": 7,
|
72 |
-
"num_hidden_layers":
|
73 |
"num_negatives": 100,
|
74 |
"pad_token_id": 24,
|
75 |
-
"proj_codevector_dim":
|
76 |
"torch_dtype": "float32",
|
77 |
"transformers_version": "4.11.3",
|
78 |
"use_weighted_layer_sum": false,
|
79 |
-
"vocab_size":
|
80 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "jonatasgrosman/wav2vec2-large-xlsr-53-german",
|
3 |
+
"activation_dropout": 0.05,
|
4 |
"apply_spec_augment": true,
|
5 |
"architectures": [
|
6 |
"Wav2Vec2ForCTC"
|
|
|
8 |
"attention_dropout": 0.5,
|
9 |
"bos_token_id": 1,
|
10 |
"classifier_proj_size": 256,
|
11 |
+
"codevector_dim": 768,
|
12 |
"contrastive_logits_temperature": 0.1,
|
13 |
+
"conv_bias": true,
|
14 |
"conv_dim": [
|
15 |
512,
|
16 |
512,
|
|
|
39 |
2
|
40 |
],
|
41 |
"ctc_loss_reduction": "mean",
|
42 |
+
"ctc_zero_infinity": true,
|
43 |
"diversity_loss_weight": 0.1,
|
44 |
+
"do_stable_layer_norm": true,
|
45 |
"eos_token_id": 2,
|
46 |
"feat_extract_activation": "gelu",
|
47 |
"feat_extract_dropout": 0.0,
|
48 |
+
"feat_extract_norm": "layer",
|
49 |
"feat_proj_dropout": 0.0,
|
50 |
"feat_quantizer_dropout": 0.0,
|
51 |
+
"final_dropout": 0.0,
|
|
|
52 |
"hidden_act": "gelu",
|
53 |
"hidden_dropout": 0.0,
|
54 |
+
"hidden_size": 1024,
|
|
|
55 |
"initializer_range": 0.02,
|
56 |
+
"intermediate_size": 4096,
|
57 |
"layer_norm_eps": 1e-05,
|
58 |
"layerdrop": 0.0,
|
59 |
+
"mask_channel_length": 10,
|
60 |
+
"mask_channel_min_space": 1,
|
61 |
+
"mask_channel_other": 0.0,
|
62 |
+
"mask_channel_prob": 0.0,
|
63 |
+
"mask_channel_selection": "static",
|
64 |
"mask_feature_length": 10,
|
65 |
"mask_feature_prob": 0.0,
|
66 |
"mask_time_length": 10,
|
67 |
+
"mask_time_min_space": 1,
|
68 |
+
"mask_time_other": 0.0,
|
69 |
"mask_time_prob": 0.05,
|
70 |
+
"mask_time_selection": "static",
|
71 |
"model_type": "wav2vec2",
|
72 |
+
"num_attention_heads": 16,
|
73 |
"num_codevector_groups": 2,
|
74 |
"num_codevectors_per_group": 320,
|
75 |
"num_conv_pos_embedding_groups": 16,
|
76 |
"num_conv_pos_embeddings": 128,
|
77 |
"num_feat_extract_layers": 7,
|
78 |
+
"num_hidden_layers": 24,
|
79 |
"num_negatives": 100,
|
80 |
"pad_token_id": 24,
|
81 |
+
"proj_codevector_dim": 768,
|
82 |
"torch_dtype": "float32",
|
83 |
"transformers_version": "4.11.3",
|
84 |
"use_weighted_layer_sum": false,
|
85 |
+
"vocab_size": 38
|
86 |
}
|
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 sha256:3d79e5fd2754fa90ea4955d2e1eb959dac8e0055d81761ad729d3ffbfd110abc
|
3 |
+
size 1262079473
|
runs/May17_01-31-58_0d0f38c34c7b/1652751127.5893614/events.out.tfevents.1652751127.0d0f38c34c7b.1404.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bcb35f8a1c11ec7a28550c52897db6ebc944e6524467107219928c0b33895f6a
|
3 |
+
size 4483
|
runs/May17_01-31-58_0d0f38c34c7b/events.out.tfevents.1652751127.0d0f38c34c7b.1404.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:904ae5272ffe16c7c21ca65d7e3190c38e14af4441a6fba4354f63069808b004
|
3 |
+
size 11921
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2799
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9eb099522910f5f0deff4d2bd83132cc3a06dd1e0148901d06b58b6760016e1
|
3 |
size 2799
|