Ilyes Rebai commited on
Commit
2c38f96
1 Parent(s): f154900

add new model with high performance

Browse files

v3.0/all_results.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 25.0,
3
+ "eval_loss": 0.4074177145957947,
4
+ "eval_mem_cpu_alloc_delta": 196608,
5
+ "eval_mem_cpu_peaked_delta": 0,
6
+ "eval_mem_gpu_alloc_delta": 0,
7
+ "eval_mem_gpu_peaked_delta": 6052522496,
8
+ "eval_runtime": 8.723,
9
+ "eval_samples": 100,
10
+ "eval_samples_per_second": 11.464,
11
+ "eval_wer": 0.3398294762484775,
12
+ "init_mem_cpu_alloc_delta": 1825918976,
13
+ "init_mem_cpu_peaked_delta": 805171200,
14
+ "init_mem_gpu_alloc_delta": 1261947904,
15
+ "init_mem_gpu_peaked_delta": 0,
16
+ "train_mem_cpu_alloc_delta": 24597475328,
17
+ "train_mem_cpu_peaked_delta": 1317408768,
18
+ "train_mem_gpu_alloc_delta": 5099735040,
19
+ "train_mem_gpu_peaked_delta": 17958715904,
20
+ "train_runtime": 258038.6163,
21
+ "train_samples": 196741,
22
+ "train_samples_per_second": 0.596
23
+ }
v3.0/config.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/workspace/output_models/wav2vec2-large-xlsr-53/checkpoint-86800",
3
+ "activation_dropout": 0.055,
4
+ "apply_spec_augment": true,
5
+ "architectures": [
6
+ "Wav2Vec2ForCTC"
7
+ ],
8
+ "attention_dropout": 0.094,
9
+ "bos_token_id": 1,
10
+ "conv_bias": true,
11
+ "conv_dim": [
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512
19
+ ],
20
+ "conv_kernel": [
21
+ 10,
22
+ 3,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 2,
27
+ 2
28
+ ],
29
+ "conv_stride": [
30
+ 5,
31
+ 2,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2
37
+ ],
38
+ "ctc_loss_reduction": "mean",
39
+ "ctc_zero_infinity": false,
40
+ "do_stable_layer_norm": true,
41
+ "eos_token_id": 2,
42
+ "feat_extract_activation": "gelu",
43
+ "feat_extract_dropout": 0.0,
44
+ "feat_extract_norm": "layer",
45
+ "feat_proj_dropout": 0.04,
46
+ "final_dropout": 0.0,
47
+ "gradient_checkpointing": true,
48
+ "hidden_act": "gelu",
49
+ "hidden_dropout": 0.047,
50
+ "hidden_size": 1024,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 4096,
53
+ "layer_norm_eps": 1e-05,
54
+ "layerdrop": 0.041,
55
+ "mask_channel_length": 10,
56
+ "mask_channel_min_space": 1,
57
+ "mask_channel_other": 0.0,
58
+ "mask_channel_prob": 0.0,
59
+ "mask_channel_selection": "static",
60
+ "mask_feature_length": 10,
61
+ "mask_feature_prob": 0.0,
62
+ "mask_time_length": 10,
63
+ "mask_time_min_space": 1,
64
+ "mask_time_other": 0.0,
65
+ "mask_time_prob": 0.2,
66
+ "mask_time_selection": "static",
67
+ "model_type": "wav2vec2",
68
+ "normalize_type": "batch",
69
+ "normalize_wav2vec": true,
70
+ "num_attention_heads": 16,
71
+ "num_conv_pos_embedding_groups": 16,
72
+ "num_conv_pos_embeddings": 128,
73
+ "num_feat_extract_layers": 7,
74
+ "num_hidden_layers": 24,
75
+ "pad_token_id": 1,
76
+ "pooling_type": "max",
77
+ "time_pooling_size": 1,
78
+ "transformers_version": "4.5.0.dev0",
79
+ "vocab_size": 47
80
+ }
v3.0/eval_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 25.0,
3
+ "eval_loss": 0.4074177145957947,
4
+ "eval_mem_cpu_alloc_delta": 196608,
5
+ "eval_mem_cpu_peaked_delta": 0,
6
+ "eval_mem_gpu_alloc_delta": 0,
7
+ "eval_mem_gpu_peaked_delta": 6052522496,
8
+ "eval_runtime": 8.723,
9
+ "eval_samples": 100,
10
+ "eval_samples_per_second": 11.464,
11
+ "eval_wer": 0.3398294762484775
12
+ }
v3.0/preprocessor_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_size": 1,
4
+ "padding_side": "right",
5
+ "padding_value": 0.0,
6
+ "return_attention_mask": true,
7
+ "sampling_rate": 16000
8
+ }
v3.0/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5effc7347c30aa34a7e713f62d14299c5873b9a1d4273a0cabc1380a2b041a8b
3
+ size 1262126615
v3.0/results.txt ADDED
@@ -0,0 +1,2 @@
 
 
1
+ WER=12.819839226606419
2
+ CER=4.402633557742363
v3.0/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
1
+ {"bos_token": "<bos>", "eos_token": "<eos>", "unk_token": "<unk>", "pad_token": "<pad>"}
v3.0/text.txt ADDED
The diff for this file is too large to render. See raw diff
v3.0/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
1
+ {"unk_token": "<unk>", "bos_token": "<bos>", "eos_token": "<eos>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|"}
v3.0/train_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 25.0,
3
+ "init_mem_cpu_alloc_delta": 1825918976,
4
+ "init_mem_cpu_peaked_delta": 805171200,
5
+ "init_mem_gpu_alloc_delta": 1261947904,
6
+ "init_mem_gpu_peaked_delta": 0,
7
+ "train_mem_cpu_alloc_delta": 24597475328,
8
+ "train_mem_cpu_peaked_delta": 1317408768,
9
+ "train_mem_gpu_alloc_delta": 5099735040,
10
+ "train_mem_gpu_peaked_delta": 17958715904,
11
+ "train_runtime": 258038.6163,
12
+ "train_samples": 196741,
13
+ "train_samples_per_second": 0.596
14
+ }
v3.0/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
v3.0/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ed6b9297b9d49f900b09f3be8454fdf14fe0bf663a49aae7ff3247892738017
3
+ size 2415
v3.0/trans.txt ADDED
The diff for this file is too large to render. See raw diff
v3.0/vocab.json ADDED
@@ -0,0 +1 @@
 
1
+ {"<unk>": 0, "<pad>": 1, "a": 2, "e": 3, "i": 4, "o": 5, "u": 6, "y": 7, "b": 8, "c": 9, "d": 10, "f": 11, "g": 12, "h": 13, "j": 14, "k": 15, "l": 16, "m": 17, "n": 18, "p": 19, "q": 20, "r": 21, "s": 22, "t": 23, "v": 24, "w": 25, "x": 26, "z": 27, "à": 28, "â": 29, "æ": 30, "ç": 31, "è": 32, "é": 33, "ê": 34, "ë": 35, "î": 36, "ï": 37, "ô": 38, "œ": 39, "ù": 40, "û": 41, "ü": 42, "ÿ": 43, "'": 44, "-": 45, "|": 46}