Training in progress, step 3000, checkpoint
Browse files- checkpoint-3000/config.json +51 -0
- checkpoint-3000/generation_config.json +168 -0
- checkpoint-3000/model-00001-of-00002.safetensors +3 -0
- checkpoint-3000/model-00002-of-00002.safetensors +3 -0
- checkpoint-3000/model.safetensors.index.json +0 -0
- checkpoint-3000/optimizer.pt +3 -0
- checkpoint-3000/preprocessor_config.json +14 -0
- checkpoint-3000/rng_state.pth +3 -0
- checkpoint-3000/scheduler.pt +3 -0
- checkpoint-3000/trainer_state.json +0 -0
- checkpoint-3000/training_args.bin +3 -0
checkpoint-3000/config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai/whisper-large-v3",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"apply_spec_augment": false,
|
6 |
+
"apply_temporal_loss": false,
|
7 |
+
"architectures": [
|
8 |
+
"CustomModel"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"begin_suppress_tokens": null,
|
12 |
+
"bos_token_id": 50257,
|
13 |
+
"classifier_proj_size": 256,
|
14 |
+
"d_model": 1280,
|
15 |
+
"decoder_attention_heads": 20,
|
16 |
+
"decoder_ffn_dim": 5120,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 32,
|
19 |
+
"decoder_start_token_id": 50258,
|
20 |
+
"dropout": 0.0,
|
21 |
+
"encoder_attention_heads": 20,
|
22 |
+
"encoder_ffn_dim": 5120,
|
23 |
+
"encoder_layerdrop": 0.0,
|
24 |
+
"encoder_layers": 32,
|
25 |
+
"eos_token_id": 50257,
|
26 |
+
"forced_decoder_ids": null,
|
27 |
+
"init_std": 0.02,
|
28 |
+
"is_encoder_decoder": true,
|
29 |
+
"mask_feature_length": 10,
|
30 |
+
"mask_feature_min_masks": 0,
|
31 |
+
"mask_feature_prob": 0.0,
|
32 |
+
"mask_time_length": 10,
|
33 |
+
"mask_time_min_masks": 2,
|
34 |
+
"mask_time_prob": 0.05,
|
35 |
+
"max_length": null,
|
36 |
+
"max_source_positions": 1500,
|
37 |
+
"max_target_positions": 448,
|
38 |
+
"median_filter_width": 7,
|
39 |
+
"model_type": "whisper",
|
40 |
+
"num_hidden_layers": 32,
|
41 |
+
"num_mel_bins": 128,
|
42 |
+
"pad_token_id": 50256,
|
43 |
+
"scale_embedding": false,
|
44 |
+
"timestamp_end_token": 51865,
|
45 |
+
"timestamp_start_token": 50365,
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.46.3",
|
48 |
+
"use_cache": true,
|
49 |
+
"use_weighted_layer_sum": false,
|
50 |
+
"vocab_size": 51866
|
51 |
+
}
|
checkpoint-3000/generation_config.json
ADDED
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alignment_heads": [
|
3 |
+
[
|
4 |
+
7,
|
5 |
+
0
|
6 |
+
],
|
7 |
+
[
|
8 |
+
10,
|
9 |
+
17
|
10 |
+
],
|
11 |
+
[
|
12 |
+
12,
|
13 |
+
18
|
14 |
+
],
|
15 |
+
[
|
16 |
+
13,
|
17 |
+
12
|
18 |
+
],
|
19 |
+
[
|
20 |
+
16,
|
21 |
+
1
|
22 |
+
],
|
23 |
+
[
|
24 |
+
17,
|
25 |
+
14
|
26 |
+
],
|
27 |
+
[
|
28 |
+
19,
|
29 |
+
11
|
30 |
+
],
|
31 |
+
[
|
32 |
+
21,
|
33 |
+
4
|
34 |
+
],
|
35 |
+
[
|
36 |
+
24,
|
37 |
+
1
|
38 |
+
],
|
39 |
+
[
|
40 |
+
25,
|
41 |
+
6
|
42 |
+
]
|
43 |
+
],
|
44 |
+
"begin_suppress_tokens": [
|
45 |
+
220,
|
46 |
+
50257
|
47 |
+
],
|
48 |
+
"bos_token_id": 50257,
|
49 |
+
"decoder_start_token_id": 50258,
|
50 |
+
"eos_token_id": 50257,
|
51 |
+
"is_multilingual": true,
|
52 |
+
"lang_to_id": {
|
53 |
+
"<|af|>": 50327,
|
54 |
+
"<|am|>": 50334,
|
55 |
+
"<|ar|>": 50272,
|
56 |
+
"<|as|>": 50350,
|
57 |
+
"<|az|>": 50304,
|
58 |
+
"<|ba|>": 50355,
|
59 |
+
"<|be|>": 50330,
|
60 |
+
"<|bg|>": 50292,
|
61 |
+
"<|bn|>": 50302,
|
62 |
+
"<|bo|>": 50347,
|
63 |
+
"<|br|>": 50309,
|
64 |
+
"<|bs|>": 50315,
|
65 |
+
"<|ca|>": 50270,
|
66 |
+
"<|cs|>": 50283,
|
67 |
+
"<|cy|>": 50297,
|
68 |
+
"<|da|>": 50285,
|
69 |
+
"<|de|>": 50261,
|
70 |
+
"<|el|>": 50281,
|
71 |
+
"<|en|>": 50259,
|
72 |
+
"<|es|>": 50262,
|
73 |
+
"<|et|>": 50307,
|
74 |
+
"<|eu|>": 50310,
|
75 |
+
"<|fa|>": 50300,
|
76 |
+
"<|fi|>": 50277,
|
77 |
+
"<|fo|>": 50338,
|
78 |
+
"<|fr|>": 50265,
|
79 |
+
"<|gl|>": 50319,
|
80 |
+
"<|gu|>": 50333,
|
81 |
+
"<|haw|>": 50352,
|
82 |
+
"<|ha|>": 50354,
|
83 |
+
"<|he|>": 50279,
|
84 |
+
"<|hi|>": 50276,
|
85 |
+
"<|hr|>": 50291,
|
86 |
+
"<|ht|>": 50339,
|
87 |
+
"<|hu|>": 50286,
|
88 |
+
"<|hy|>": 50312,
|
89 |
+
"<|id|>": 50275,
|
90 |
+
"<|is|>": 50311,
|
91 |
+
"<|it|>": 50274,
|
92 |
+
"<|ja|>": 50266,
|
93 |
+
"<|jw|>": 50356,
|
94 |
+
"<|ka|>": 50329,
|
95 |
+
"<|kk|>": 50316,
|
96 |
+
"<|km|>": 50323,
|
97 |
+
"<|kn|>": 50306,
|
98 |
+
"<|ko|>": 50264,
|
99 |
+
"<|la|>": 50294,
|
100 |
+
"<|lb|>": 50345,
|
101 |
+
"<|ln|>": 50353,
|
102 |
+
"<|lo|>": 50336,
|
103 |
+
"<|lt|>": 50293,
|
104 |
+
"<|lv|>": 50301,
|
105 |
+
"<|mg|>": 50349,
|
106 |
+
"<|mi|>": 50295,
|
107 |
+
"<|mk|>": 50308,
|
108 |
+
"<|ml|>": 50296,
|
109 |
+
"<|mn|>": 50314,
|
110 |
+
"<|mr|>": 50320,
|
111 |
+
"<|ms|>": 50282,
|
112 |
+
"<|mt|>": 50343,
|
113 |
+
"<|my|>": 50346,
|
114 |
+
"<|ne|>": 50313,
|
115 |
+
"<|nl|>": 50271,
|
116 |
+
"<|nn|>": 50342,
|
117 |
+
"<|no|>": 50288,
|
118 |
+
"<|oc|>": 50328,
|
119 |
+
"<|pa|>": 50321,
|
120 |
+
"<|pl|>": 50269,
|
121 |
+
"<|ps|>": 50340,
|
122 |
+
"<|pt|>": 50267,
|
123 |
+
"<|ro|>": 50284,
|
124 |
+
"<|ru|>": 50263,
|
125 |
+
"<|sa|>": 50344,
|
126 |
+
"<|sd|>": 50332,
|
127 |
+
"<|si|>": 50322,
|
128 |
+
"<|sk|>": 50298,
|
129 |
+
"<|sl|>": 50305,
|
130 |
+
"<|sn|>": 50324,
|
131 |
+
"<|so|>": 50326,
|
132 |
+
"<|sq|>": 50317,
|
133 |
+
"<|sr|>": 50303,
|
134 |
+
"<|su|>": 50357,
|
135 |
+
"<|sv|>": 50273,
|
136 |
+
"<|sw|>": 50318,
|
137 |
+
"<|ta|>": 50287,
|
138 |
+
"<|te|>": 50299,
|
139 |
+
"<|tg|>": 50331,
|
140 |
+
"<|th|>": 50289,
|
141 |
+
"<|tk|>": 50341,
|
142 |
+
"<|tl|>": 50348,
|
143 |
+
"<|tr|>": 50268,
|
144 |
+
"<|tt|>": 50351,
|
145 |
+
"<|uk|>": 50280,
|
146 |
+
"<|ur|>": 50290,
|
147 |
+
"<|uz|>": 50337,
|
148 |
+
"<|vi|>": 50278,
|
149 |
+
"<|yi|>": 50335,
|
150 |
+
"<|yo|>": 50325,
|
151 |
+
"<|yue|>": 50358,
|
152 |
+
"<|zh|>": 50260
|
153 |
+
},
|
154 |
+
"language": null,
|
155 |
+
"max_initial_timestamp_index": 50,
|
156 |
+
"max_length": 448,
|
157 |
+
"no_timestamps_token_id": 50364,
|
158 |
+
"pad_token_id": 50257,
|
159 |
+
"prev_sot_token_id": 50362,
|
160 |
+
"return_timestamps": false,
|
161 |
+
"suppress_tokens": [],
|
162 |
+
"task": "transcribe",
|
163 |
+
"task_to_id": {
|
164 |
+
"transcribe": 50360,
|
165 |
+
"translate": 50359
|
166 |
+
},
|
167 |
+
"transformers_version": "4.46.3"
|
168 |
+
}
|
checkpoint-3000/model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39b385f42b4415d630df2b07c3155fff10382f8fb49bb24a390c8b244e3dee7f
|
3 |
+
size 4993448880
|
checkpoint-3000/model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6b104611822e9c2234ccb6533ea9566e3dd0762ad655a4b87de673a8c22d7a9
|
3 |
+
size 1180663192
|
checkpoint-3000/model.safetensors.index.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f514a8ec4fd4b4f6272f06563e65d0a3562d89fe324a4279351462c3d582837
|
3 |
+
size 12333660476
|
checkpoint-3000/preprocessor_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chunk_length": 30,
|
3 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
4 |
+
"feature_size": 128,
|
5 |
+
"hop_length": 160,
|
6 |
+
"n_fft": 400,
|
7 |
+
"n_samples": 480000,
|
8 |
+
"nb_max_frames": 3000,
|
9 |
+
"padding_side": "right",
|
10 |
+
"padding_value": 0.0,
|
11 |
+
"processor_class": "WhisperProcessor",
|
12 |
+
"return_attention_mask": false,
|
13 |
+
"sampling_rate": 16000
|
14 |
+
}
|
checkpoint-3000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3555fa0825d4236680135b65cab80bc5215392809e8564d2cce9e7d75f5c122c
|
3 |
+
size 14244
|
checkpoint-3000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2506a21044c938f92fd2c90d9e5033335dc6cbbe1ed63badee60b60e99ef02ee
|
3 |
+
size 1064
|
checkpoint-3000/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-3000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f2c9d4167b7b0910073abbab06b3c2f70f49b20c90b9e246baf87b0d93b65e26
|
3 |
+
size 5496
|