Lakoc commited on
Commit
f9e3f67
1 Parent(s): 0b3b62c

End of training

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ predictions_common_voice_13_en_common_voice_13_en_test_wer71.35_hyp.trn.snt.utt filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: Lakoc/DeCRED_small_cv_2
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice_13_0
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: DeCRED_small_cv_v2_scalar_mixing
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # DeCRED_small_cv_v2_scalar_mixing
18
+
19
+ This model is a fine-tuned version of [Lakoc/DeCRED_small_cv_2](https://huggingface.co/Lakoc/DeCRED_small_cv_2) on the common_voice_13_0 dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 2.0838
22
+ - Cer: 0.4056
23
+ - Wer: 0.6611
24
+ - Mer: 0.5983
25
+ - Wil: 0.8066
26
+ - Wip: 0.1934
27
+ - Hits: 20649
28
+ - Substitutions: 21863
29
+ - Deletions: 4009
30
+ - Insertions: 4882
31
+
32
+ ## Model description
33
+
34
+ More information needed
35
+
36
+ ## Intended uses & limitations
37
+
38
+ More information needed
39
+
40
+ ## Training and evaluation data
41
+
42
+ More information needed
43
+
44
+ ## Training procedure
45
+
46
+ ### Training hyperparameters
47
+
48
+ The following hyperparameters were used during training:
49
+ - learning_rate: 0.0005
50
+ - train_batch_size: 128
51
+ - eval_batch_size: 128
52
+ - seed: 42
53
+ - distributed_type: multi-GPU
54
+ - num_devices: 2
55
+ - gradient_accumulation_steps: 2
56
+ - total_train_batch_size: 512
57
+ - total_eval_batch_size: 256
58
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - num_epochs: 50.0
61
+
62
+ ### Training results
63
+
64
+ | Training Loss | Epoch | Step | Validation Loss | Cer | Wer | Mer | Wil | Wip | Hits | Substitutions | Deletions | Insertions |
65
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:------:|:------:|:------:|:-----:|:-------------:|:---------:|:----------:|
66
+ | 6.9657 | 0.98 | 22 | 6.8485 | 59.9990 | 50.8263 | 0.9996 | 1.0000 | 0.0000 | 909 | 45605 | 7 | 2318877 |
67
+ | 6.585 | 2.0 | 45 | 6.6096 | 60.0578 | 50.5684 | 0.9996 | 1.0000 | 0.0000 | 990 | 45524 | 7 | 2306961 |
68
+ | 6.479 | 2.98 | 67 | 6.3875 | 59.6307 | 50.1500 | 0.9996 | 1.0000 | 0.0000 | 1046 | 45464 | 11 | 2287554 |
69
+ | 6.1764 | 4.0 | 90 | 6.1618 | 58.9125 | 49.4174 | 0.9995 | 1.0000 | 0.0000 | 1100 | 45410 | 11 | 2253527 |
70
+ | 6.0943 | 4.98 | 112 | 5.9524 | 57.6932 | 48.3373 | 0.9995 | 1.0000 | 0.0000 | 1191 | 45307 | 23 | 2203369 |
71
+ | 5.7875 | 6.0 | 135 | 5.7400 | 56.4049 | 47.1201 | 0.9994 | 1.0000 | 0.0000 | 1350 | 45145 | 26 | 2146902 |
72
+ | 5.7306 | 6.98 | 157 | 5.5433 | 55.1239 | 46.0142 | 0.9993 | 1.0000 | 0.0000 | 1449 | 45043 | 29 | 2095554 |
73
+ | 5.3893 | 8.0 | 180 | 5.3443 | 53.1765 | 44.2142 | 0.9992 | 1.0000 | 0.0000 | 1609 | 44876 | 36 | 2011978 |
74
+ | 5.355 | 8.98 | 202 | 5.1604 | 50.8395 | 42.2829 | 0.9991 | 1.0000 | 0.0000 | 1726 | 44743 | 52 | 1922250 |
75
+ | 5.0009 | 10.0 | 225 | 4.9748 | 47.9798 | 39.7937 | 0.9990 | 1.0000 | 0.0000 | 1921 | 44525 | 75 | 1806641 |
76
+ | 4.9572 | 10.98 | 247 | 4.8037 | 44.5128 | 36.9002 | 0.9988 | 0.9999 | 0.0001 | 2039 | 44377 | 105 | 1672151 |
77
+ | 4.7249 | 12.0 | 270 | 4.6314 | 40.9512 | 34.0044 | 0.9985 | 0.9999 | 0.0001 | 2306 | 44103 | 112 | 1537704 |
78
+ | 4.5906 | 12.98 | 292 | 4.4729 | 36.5890 | 30.3183 | 0.9982 | 0.9999 | 0.0001 | 2542 | 43829 | 150 | 1366459 |
79
+ | 4.3943 | 14.0 | 315 | 4.3138 | 32.2323 | 26.6965 | 0.9978 | 0.9999 | 0.0001 | 2765 | 43562 | 194 | 1198191 |
80
+ | 4.3164 | 14.98 | 337 | 4.1678 | 28.0206 | 23.2171 | 0.9972 | 0.9998 | 0.0002 | 3042 | 43206 | 273 | 1036603 |
81
+ | 4.1206 | 16.0 | 360 | 4.0216 | 23.6627 | 19.7857 | 0.9964 | 0.9997 | 0.0003 | 3295 | 42841 | 385 | 877224 |
82
+ | 4.0375 | 16.98 | 382 | 3.8879 | 19.1286 | 16.0039 | 0.9952 | 0.9996 | 0.0004 | 3622 | 42341 | 558 | 701619 |
83
+ | 3.8357 | 18.0 | 405 | 3.7545 | 15.4344 | 12.9968 | 0.9934 | 0.9994 | 0.0006 | 3991 | 41883 | 647 | 562094 |
84
+ | 3.7535 | 18.98 | 427 | 3.6327 | 11.6498 | 9.9882 | 0.9907 | 0.9991 | 0.0009 | 4356 | 41365 | 800 | 422498 |
85
+ | 3.5453 | 20.0 | 450 | 3.5116 | 9.0630 | 7.8157 | 0.9872 | 0.9987 | 0.0013 | 4705 | 40852 | 964 | 321778 |
86
+ | 3.5829 | 20.98 | 472 | 3.4015 | 6.9251 | 6.0536 | 0.9817 | 0.9979 | 0.0021 | 5240 | 40091 | 1190 | 240338 |
87
+ | 3.3805 | 22.0 | 495 | 3.2922 | 5.3260 | 4.7628 | 0.9754 | 0.9970 | 0.0030 | 5588 | 39576 | 1357 | 180635 |
88
+ | 3.3505 | 22.98 | 517 | 3.1933 | 3.7440 | 3.4844 | 0.9640 | 0.9953 | 0.0047 | 6051 | 38927 | 1543 | 121630 |
89
+ | 3.1605 | 24.0 | 540 | 3.0954 | 2.8455 | 2.7410 | 0.9505 | 0.9928 | 0.0072 | 6644 | 38101 | 1776 | 87636 |
90
+ | 3.1195 | 24.98 | 562 | 3.0071 | 1.8640 | 1.9752 | 0.9279 | 0.9887 | 0.0113 | 7141 | 37306 | 2074 | 52510 |
91
+ | 3.0494 | 26.0 | 585 | 2.9201 | 1.7379 | 1.8401 | 0.9164 | 0.9856 | 0.0144 | 7812 | 36313 | 2396 | 46896 |
92
+ | 3.0038 | 26.98 | 607 | 2.8418 | 1.3510 | 1.5287 | 0.8936 | 0.9800 | 0.0200 | 8466 | 35489 | 2566 | 33062 |
93
+ | 2.8702 | 28.0 | 630 | 2.7651 | 1.0949 | 1.3176 | 0.8699 | 0.9733 | 0.0267 | 9170 | 34524 | 2827 | 23947 |
94
+ | 2.8388 | 28.98 | 652 | 2.6963 | 0.9275 | 1.1758 | 0.8480 | 0.9664 | 0.0336 | 9802 | 33665 | 3054 | 17981 |
95
+ | 2.7353 | 30.0 | 675 | 2.6292 | 0.7931 | 1.0642 | 0.8230 | 0.9572 | 0.0428 | 10649 | 32622 | 3250 | 13637 |
96
+ | 2.694 | 30.98 | 697 | 2.5693 | 0.7406 | 1.0138 | 0.8049 | 0.9491 | 0.0509 | 11429 | 31693 | 3399 | 12071 |
97
+ | 2.63 | 32.0 | 720 | 2.5112 | 0.6716 | 0.9492 | 0.7835 | 0.9395 | 0.0605 | 12203 | 30845 | 3473 | 9839 |
98
+ | 2.5981 | 32.98 | 742 | 2.4596 | 0.6256 | 0.9070 | 0.7648 | 0.9298 | 0.0702 | 12979 | 29960 | 3582 | 8653 |
99
+ | 2.521 | 34.0 | 765 | 2.4099 | 0.5947 | 0.8741 | 0.7464 | 0.9192 | 0.0808 | 13813 | 29004 | 3704 | 7957 |
100
+ | 2.5005 | 34.98 | 787 | 2.3661 | 0.5715 | 0.8503 | 0.7324 | 0.9105 | 0.0895 | 14454 | 28259 | 3808 | 7488 |
101
+ | 2.4067 | 36.0 | 810 | 2.3241 | 0.5436 | 0.8208 | 0.7145 | 0.8991 | 0.1009 | 15259 | 27414 | 3848 | 6923 |
102
+ | 2.3969 | 36.98 | 832 | 2.2875 | 0.5252 | 0.8022 | 0.7004 | 0.8890 | 0.1110 | 15966 | 26612 | 3943 | 6765 |
103
+ | 2.3816 | 38.0 | 855 | 2.2529 | 0.5033 | 0.7763 | 0.6837 | 0.8772 | 0.1228 | 16710 | 25846 | 3965 | 6302 |
104
+ | 2.3544 | 38.98 | 877 | 2.2230 | 0.4892 | 0.7597 | 0.6709 | 0.8673 | 0.1327 | 17339 | 25191 | 3991 | 6159 |
105
+ | 2.2744 | 40.0 | 900 | 2.1951 | 0.4719 | 0.7402 | 0.6570 | 0.8565 | 0.1435 | 17977 | 24541 | 4003 | 5893 |
106
+ | 2.2653 | 40.98 | 922 | 2.1715 | 0.4591 | 0.7252 | 0.6454 | 0.8470 | 0.1530 | 18532 | 23960 | 4029 | 5747 |
107
+ | 2.2736 | 42.0 | 945 | 2.1500 | 0.4461 | 0.7092 | 0.6345 | 0.8382 | 0.1618 | 19009 | 23522 | 3990 | 5482 |
108
+ | 2.256 | 42.98 | 967 | 2.1324 | 0.4347 | 0.6953 | 0.6240 | 0.8294 | 0.1706 | 19489 | 23062 | 3970 | 5313 |
109
+ | 2.2187 | 44.0 | 990 | 2.1170 | 0.4265 | 0.6852 | 0.6164 | 0.8227 | 0.1773 | 19834 | 22682 | 4005 | 5187 |
110
+ | 2.2122 | 44.98 | 1012 | 2.1050 | 0.4187 | 0.6755 | 0.6094 | 0.8166 | 0.1834 | 20141 | 22360 | 4020 | 5044 |
111
+ | 2.2259 | 46.0 | 1035 | 2.0954 | 0.4126 | 0.6690 | 0.6045 | 0.8123 | 0.1877 | 20360 | 22162 | 3999 | 4963 |
112
+ | 2.2367 | 46.98 | 1057 | 2.0889 | 0.4087 | 0.6642 | 0.6007 | 0.8088 | 0.1912 | 20538 | 21978 | 4005 | 4916 |
113
+ | 2.1789 | 48.0 | 1080 | 2.0849 | 0.4062 | 0.6617 | 0.5988 | 0.8071 | 0.1929 | 20623 | 21886 | 4012 | 4887 |
114
+ | 2.0912 | 48.89 | 1100 | 2.0838 | 0.4056 | 0.6611 | 0.5983 | 0.8066 | 0.1934 | 20649 | 21863 | 4009 | 4882 |
115
+
116
+
117
+ ### Framework versions
118
+
119
+ - Transformers 4.40.0.dev0
120
+ - Pytorch 2.2.0+rocm5.6
121
+ - Datasets 2.18.0
122
+ - Tokenizers 0.15.2
config.json ADDED
@@ -0,0 +1,276 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Lakoc/DeCRED_small_cv_2",
3
+ "architectures": [
4
+ "JointCTCAttentionEncoderDecoder"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "ctc_weight": 0.3,
8
+ "decoder": {
9
+ "_name_or_path": "Lakoc/gpt2_256h_6l_add_head3_04",
10
+ "activation_function": "gelu_new",
11
+ "add_cross_attention": true,
12
+ "architectures": null,
13
+ "attn_pdrop": 0.1,
14
+ "average_logits": false,
15
+ "bad_words_ids": null,
16
+ "begin_suppress_tokens": null,
17
+ "bos_token_id": 0,
18
+ "chunk_size_feed_forward": 0,
19
+ "cross_attention_hidden_size": null,
20
+ "decoder_start_token_id": null,
21
+ "diversity_penalty": 0.0,
22
+ "do_sample": false,
23
+ "early_stopping": false,
24
+ "embd_pdrop": 0.1,
25
+ "encoder_no_repeat_ngram_size": 0,
26
+ "eos_token_id": 1,
27
+ "exponential_decay_length_penalty": null,
28
+ "finetuning_task": null,
29
+ "forced_bos_token_id": null,
30
+ "forced_eos_token_id": null,
31
+ "head_locations": [
32
+ 3
33
+ ],
34
+ "head_weights": [
35
+ 0.6,
36
+ 0.4
37
+ ],
38
+ "id2label": {
39
+ "0": "LABEL_0",
40
+ "1": "LABEL_1"
41
+ },
42
+ "initializer_range": 0.02,
43
+ "is_decoder": true,
44
+ "is_encoder_decoder": false,
45
+ "label2id": {
46
+ "LABEL_0": 0,
47
+ "LABEL_1": 1
48
+ },
49
+ "layer_norm_epsilon": 1e-05,
50
+ "length_penalty": 1.0,
51
+ "max_length": 20,
52
+ "min_length": 0,
53
+ "model_type": "gpt2-multi-head",
54
+ "n_embd": 256,
55
+ "n_head": 4,
56
+ "n_inner": 2048,
57
+ "n_layer": 6,
58
+ "n_positions": 1024,
59
+ "no_repeat_ngram_size": 0,
60
+ "num_beam_groups": 1,
61
+ "num_beams": 1,
62
+ "num_return_sequences": 1,
63
+ "output_attentions": false,
64
+ "output_hidden_states": false,
65
+ "output_scores": false,
66
+ "pad_token_id": null,
67
+ "pos_emb_fixed": true,
68
+ "prefix": null,
69
+ "problem_type": null,
70
+ "pruned_heads": {},
71
+ "remove_invalid_values": false,
72
+ "reorder_and_upcast_attn": false,
73
+ "repetition_penalty": 1.0,
74
+ "resid_pdrop": 0.1,
75
+ "return_dict": true,
76
+ "return_dict_in_generate": false,
77
+ "scale_attn_by_inverse_layer_idx": false,
78
+ "scale_attn_weights": true,
79
+ "sep_token_id": null,
80
+ "summary_activation": null,
81
+ "summary_first_dropout": 0.1,
82
+ "summary_proj_to_labels": true,
83
+ "summary_type": "cls_index",
84
+ "summary_use_proj": true,
85
+ "suppress_tokens": null,
86
+ "task_specific_params": null,
87
+ "temperature": 1.0,
88
+ "tf_legacy_loss": false,
89
+ "tie_additional_weights": false,
90
+ "tie_encoder_decoder": false,
91
+ "tie_word_embeddings": false,
92
+ "tokenizer_class": null,
93
+ "top_k": 50,
94
+ "top_p": 1.0,
95
+ "torch_dtype": null,
96
+ "torchscript": false,
97
+ "typical_p": 1.0,
98
+ "use_bfloat16": false,
99
+ "use_cache": true,
100
+ "vocab_size": 1000
101
+ },
102
+ "decoder_start_token_id": 0,
103
+ "encoder": {
104
+ "_name_or_path": "Lakoc/fisher_ebranchformer_enc_12_layers_fixed",
105
+ "activation_dropout": 0.1,
106
+ "adapter_attn_dim": null,
107
+ "adapter_kernel_size": 3,
108
+ "adapter_stride": 2,
109
+ "add_adapter": false,
110
+ "add_cross_attention": false,
111
+ "apply_spec_augment": false,
112
+ "architectures": null,
113
+ "attention_dropout": 0.1,
114
+ "bad_words_ids": null,
115
+ "begin_suppress_tokens": null,
116
+ "bos_token_id": 1,
117
+ "chunk_size_feed_forward": 0,
118
+ "classifier_proj_size": 256,
119
+ "codevector_dim": 256,
120
+ "conformer_conv_dropout": 0.1,
121
+ "contrastive_logits_temperature": 0.1,
122
+ "conv_bias": false,
123
+ "conv_depthwise_kernel_size": 31,
124
+ "conv_dim": [
125
+ 256,
126
+ 256
127
+ ],
128
+ "conv_kernel": [
129
+ 3,
130
+ 3
131
+ ],
132
+ "conv_padding": [
133
+ 1,
134
+ 1
135
+ ],
136
+ "conv_stride": [
137
+ 2,
138
+ 2
139
+ ],
140
+ "cross_attention_hidden_size": null,
141
+ "csgu_activation": "identity",
142
+ "csgu_conv_dropout": 0.1,
143
+ "csgu_kernel_size": 31,
144
+ "csgu_use_linear_after_conv": false,
145
+ "ctc_loss_reduction": "mean",
146
+ "ctc_zero_infinity": true,
147
+ "decoder_start_token_id": null,
148
+ "diversity_loss_weight": 0.1,
149
+ "diversity_penalty": 0.0,
150
+ "do_sample": false,
151
+ "do_stable_layer_norm": false,
152
+ "early_stopping": false,
153
+ "encoder_no_repeat_ngram_size": 0,
154
+ "eos_token_id": 2,
155
+ "exponential_decay_length_penalty": null,
156
+ "fe_position_embeddings": false,
157
+ "feat_extract_activation": "gelu",
158
+ "feat_extract_norm": "group",
159
+ "feat_proj_dropout": 0.0,
160
+ "feat_quantizer_dropout": 0.0,
161
+ "final_dropout": 0.1,
162
+ "finetuning_task": null,
163
+ "forced_bos_token_id": null,
164
+ "forced_eos_token_id": null,
165
+ "hidden_act": "gelu",
166
+ "hidden_dropout": 0.1,
167
+ "hidden_size": 256,
168
+ "id2label": {
169
+ "0": "LABEL_0",
170
+ "1": "LABEL_1"
171
+ },
172
+ "initializer_range": 0.02,
173
+ "intermediate_size": 1024,
174
+ "is_causal": false,
175
+ "is_decoder": false,
176
+ "is_encoder_decoder": false,
177
+ "label2id": {
178
+ "LABEL_0": 0,
179
+ "LABEL_1": 1
180
+ },
181
+ "layer_norm_eps": 1e-05,
182
+ "layerdrop": 0.0,
183
+ "length_penalty": 1.0,
184
+ "mask_feature_length": 10,
185
+ "mask_feature_min_masks": 0,
186
+ "mask_feature_prob": 0.0,
187
+ "mask_time_length": 10,
188
+ "mask_time_min_masks": 2,
189
+ "mask_time_prob": 0.05,
190
+ "max_length": 20,
191
+ "max_source_positions": 1024,
192
+ "merge_conv_kernel": 31,
193
+ "min_length": 0,
194
+ "model_type": "wav2vec2-ebranchformer",
195
+ "no_repeat_ngram_size": 0,
196
+ "num_adapter_layers": 3,
197
+ "num_attention_heads": 4,
198
+ "num_beam_groups": 1,
199
+ "num_beams": 1,
200
+ "num_codevector_groups": 2,
201
+ "num_codevectors_per_group": 320,
202
+ "num_conv_pos_embedding_groups": 16,
203
+ "num_conv_pos_embeddings": 128,
204
+ "num_fbanks": 80,
205
+ "num_feat_extract_layers": 2,
206
+ "num_hidden_layers": 12,
207
+ "num_mel_bins": 80,
208
+ "num_negatives": 100,
209
+ "num_return_sequences": 1,
210
+ "output_attentions": false,
211
+ "output_hidden_size": 256,
212
+ "output_hidden_states": false,
213
+ "output_scores": false,
214
+ "pad_token_id": 3,
215
+ "position_embeddings_type": "relative",
216
+ "prefix": null,
217
+ "problem_type": null,
218
+ "proj_codevector_dim": 256,
219
+ "pruned_heads": {},
220
+ "remove_invalid_values": false,
221
+ "repetition_penalty": 1.0,
222
+ "return_dict": true,
223
+ "return_dict_in_generate": false,
224
+ "rotary_embedding_base": 10000,
225
+ "sep_token_id": null,
226
+ "suppress_tokens": null,
227
+ "task_specific_params": null,
228
+ "tdnn_dilation": [
229
+ 1,
230
+ 2,
231
+ 3,
232
+ 1,
233
+ 1
234
+ ],
235
+ "tdnn_dim": [
236
+ 512,
237
+ 512,
238
+ 512,
239
+ 512,
240
+ 1500
241
+ ],
242
+ "tdnn_kernel": [
243
+ 5,
244
+ 3,
245
+ 3,
246
+ 1,
247
+ 1
248
+ ],
249
+ "temperature": 1.0,
250
+ "tf_legacy_loss": false,
251
+ "tie_encoder_decoder": false,
252
+ "tie_word_embeddings": true,
253
+ "tokenizer_class": null,
254
+ "top_k": 50,
255
+ "top_p": 1.0,
256
+ "torch_dtype": null,
257
+ "torchscript": false,
258
+ "typical_p": 1.0,
259
+ "use_bfloat16": false,
260
+ "use_fbanks": true,
261
+ "use_macaron_ff": true,
262
+ "use_weighted_layer_sum": false,
263
+ "vocab_size": 1000,
264
+ "xvector_output_dim": 512
265
+ },
266
+ "eos_token_id": 1,
267
+ "is_encoder_decoder": true,
268
+ "lsm_factor": 0.1,
269
+ "mask_token_id": 4,
270
+ "model_type": "joint_aed_ctc_speech-encoder-decoder",
271
+ "pad_token_id": 3,
272
+ "shared_lm_head": false,
273
+ "tie_word_embeddings": false,
274
+ "torch_dtype": "float32",
275
+ "transformers_version": "4.40.0.dev0"
276
+ }
generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "apply_eos_space_trick": false,
3
+ "bos_token_id": 0,
4
+ "ctc_margin": 0,
5
+ "ctc_weight": 0.0,
6
+ "decoder_start_token_id": 0,
7
+ "eos_space_trick_weight": 0.0,
8
+ "eos_token_id": 1,
9
+ "lm_model": null,
10
+ "lm_weight": 0.0,
11
+ "max_length": 512,
12
+ "pad_token_id": 3,
13
+ "space_token_id": -1,
14
+ "transformers_version": "4.40.0.dev0"
15
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa700d1b8fdbab73726eab0ca8cfb157e982fe0dc88850b1227341b823a7742
3
+ size 144243304
predictions_common_voice_13_en_common_voice_13_en_test_wer71.35.csv ADDED
The diff for this file is too large to render. See raw diff
 
predictions_common_voice_13_en_common_voice_13_en_test_wer71.35_hyp.trn ADDED
The diff for this file is too large to render. See raw diff
 
predictions_common_voice_13_en_common_voice_13_en_test_wer71.35_hyp.trn.dtl ADDED
The diff for this file is too large to render. See raw diff
 
predictions_common_voice_13_en_common_voice_13_en_test_wer71.35_hyp.trn.snt.utt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d06f30ea36d39336d4fd01f852e7fff2c26dcdfb8e8bff866d6d375fe4626043
3
+ size 12001794
predictions_common_voice_13_en_common_voice_13_en_test_wer71.35_hyp.trn.sys ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+
3
+
4
+ SYSTEM SUMMARY PERCENTAGES by SPEAKER
5
+
6
+ ,------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------.
7
+ |/scratch/project_465000836/ipoloka/huggingface_asr/experiments/decred/commonvoice/DeCRED_small_cv_v2_scalar_mixing/predictions_common_voice_13_en_common_voice_13_en_test_wer71.35_hyp.trn|
8
+ |------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
9
+ | SPKR | # Snt # Wrd | Corr Sub Del Ins Err S.Err |
10
+ |---------------------+--------------------------------------------+-----------------------------------------------------------------------------------------------------------------------|
11
+ | utt | 16384 144172 | 42.0 48.4 9.6 13.3 71.3 99.8 |
12
+ |==========================================================================================================================================================================================|
13
+ | Sum/Avg | 16384 144172 | 42.0 48.4 9.6 13.3 71.3 99.8 |
14
+ |==========================================================================================================================================================================================|
15
+ | Mean | 16384.0 144172.0 | 42.0 48.4 9.6 13.3 71.3 99.8 |
16
+ | S.D. | 0.0 0.0 | 0.0 0.0 0.0 0.0 0.0 0.0 |
17
+ | Median | 16384.0 144172.0 | 42.0 48.4 9.6 13.3 71.3 99.8 |
18
+ `------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------'
predictions_common_voice_13_en_common_voice_13_en_test_wer71.35_ref.trn ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80ae0ca3847a297364ac7b350ce61efa09b675abb7969a71b002df9b2c1bcc93
3
+ size 5752