KarthikAvinash commited on
Commit
63ae639
1 Parent(s): d74f729

Training in progress, step 1

Browse files
config.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/whisper-medium",
3
+ "activation_dropout": 0.0,
4
+ "activation_function": "gelu",
5
+ "apply_spec_augment": false,
6
+ "architectures": [
7
+ "WhisperForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "begin_suppress_tokens": [
11
+ 220,
12
+ 50257
13
+ ],
14
+ "bos_token_id": 50257,
15
+ "classifier_proj_size": 256,
16
+ "d_model": 1024,
17
+ "decoder_attention_heads": 16,
18
+ "decoder_ffn_dim": 4096,
19
+ "decoder_layerdrop": 0.0,
20
+ "decoder_layers": 24,
21
+ "decoder_start_token_id": 50258,
22
+ "dropout": 0.0,
23
+ "encoder_attention_heads": 16,
24
+ "encoder_ffn_dim": 4096,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 24,
27
+ "eos_token_id": 50257,
28
+ "forced_decoder_ids": null,
29
+ "init_std": 0.02,
30
+ "is_encoder_decoder": true,
31
+ "mask_feature_length": 10,
32
+ "mask_feature_min_masks": 0,
33
+ "mask_feature_prob": 0.0,
34
+ "mask_time_length": 10,
35
+ "mask_time_min_masks": 2,
36
+ "mask_time_prob": 0.05,
37
+ "max_length": 448,
38
+ "max_source_positions": 1500,
39
+ "max_target_positions": 448,
40
+ "median_filter_width": 7,
41
+ "model_type": "whisper",
42
+ "num_hidden_layers": 24,
43
+ "num_mel_bins": 80,
44
+ "pad_token_id": 50257,
45
+ "scale_embedding": false,
46
+ "suppress_tokens": [
47
+ 1,
48
+ 2,
49
+ 7,
50
+ 8,
51
+ 9,
52
+ 10,
53
+ 14,
54
+ 25,
55
+ 26,
56
+ 27,
57
+ 28,
58
+ 29,
59
+ 31,
60
+ 58,
61
+ 59,
62
+ 60,
63
+ 61,
64
+ 62,
65
+ 63,
66
+ 90,
67
+ 91,
68
+ 92,
69
+ 93,
70
+ 359,
71
+ 503,
72
+ 522,
73
+ 542,
74
+ 873,
75
+ 893,
76
+ 902,
77
+ 918,
78
+ 922,
79
+ 931,
80
+ 1350,
81
+ 1853,
82
+ 1982,
83
+ 2460,
84
+ 2627,
85
+ 3246,
86
+ 3253,
87
+ 3268,
88
+ 3536,
89
+ 3846,
90
+ 3961,
91
+ 4183,
92
+ 4667,
93
+ 6585,
94
+ 6647,
95
+ 7273,
96
+ 9061,
97
+ 9383,
98
+ 10428,
99
+ 10929,
100
+ 11938,
101
+ 12033,
102
+ 12331,
103
+ 12562,
104
+ 13793,
105
+ 14157,
106
+ 14635,
107
+ 15265,
108
+ 15618,
109
+ 16553,
110
+ 16604,
111
+ 18362,
112
+ 18956,
113
+ 20075,
114
+ 21675,
115
+ 22520,
116
+ 26130,
117
+ 26161,
118
+ 26435,
119
+ 28279,
120
+ 29464,
121
+ 31650,
122
+ 32302,
123
+ 32470,
124
+ 36865,
125
+ 42863,
126
+ 47425,
127
+ 49870,
128
+ 50254,
129
+ 50258,
130
+ 50358,
131
+ 50359,
132
+ 50360,
133
+ 50361,
134
+ 50362
135
+ ],
136
+ "supress_tokens": [],
137
+ "torch_dtype": "float32",
138
+ "transformers_version": "4.43.0.dev0",
139
+ "use_cache": false,
140
+ "use_weighted_layer_sum": false,
141
+ "vocab_size": 51865
142
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ece2365d57be8f99c006b31ad4514c10d1086c81543b691b7b0c7bcda3b4c45
3
+ size 3055544304
runs/Jul31_11-16-21_DESKTOP-C5U12HF/events.out.tfevents.1722404810.DESKTOP-C5U12HF.14032.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daa6d9ada8446712d433a1e662f542976c79dcf5c320924a6de423df79bde411
3
+ size 7101
runs/Jul31_11-21-11_DESKTOP-C5U12HF/events.out.tfevents.1722405079.DESKTOP-C5U12HF.14032.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dc25e67fc593b968949fece26127f06c6e34b6c6b3a115444ecf4fb490cb31e
3
+ size 6892
runs/Jul31_11-31-36_DESKTOP-C5U12HF/events.out.tfevents.1722405698.DESKTOP-C5U12HF.14032.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dac477c0bff3a9e31016f48344146bdde5b1f32584a64503795739d6dc7d2c1
3
+ size 7204
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b63e81243886b79632b0dd663ccb29e2ce5a254e82d36243a56cde274b1cf57
3
+ size 5368