Training in progress, step 3686, checkpoint
Browse files- checkpoint-3686/config.json +47 -0
- checkpoint-3686/generation_config.json +159 -0
- checkpoint-3686/model.safetensors +3 -0
- checkpoint-3686/optimizer.pt +3 -0
- checkpoint-3686/preprocessor_config.json +15 -0
- checkpoint-3686/rng_state.pth +3 -0
- checkpoint-3686/scheduler.pt +3 -0
- checkpoint-3686/trainer_state.json +0 -0
- checkpoint-3686/training_args.bin +3 -0
checkpoint-3686/config.json
ADDED
|
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"apply_spec_augment": false,
|
| 5 |
+
"architectures": [
|
| 6 |
+
"WhisperForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"begin_suppress_tokens": null,
|
| 10 |
+
"bos_token_id": 50257,
|
| 11 |
+
"classifier_proj_size": 256,
|
| 12 |
+
"d_model": 512,
|
| 13 |
+
"decoder_attention_heads": 8,
|
| 14 |
+
"decoder_ffn_dim": 2048,
|
| 15 |
+
"decoder_layerdrop": 0.0,
|
| 16 |
+
"decoder_layers": 6,
|
| 17 |
+
"decoder_start_token_id": 50258,
|
| 18 |
+
"dropout": 0.0,
|
| 19 |
+
"encoder_attention_heads": 8,
|
| 20 |
+
"encoder_ffn_dim": 2048,
|
| 21 |
+
"encoder_layerdrop": 0.0,
|
| 22 |
+
"encoder_layers": 6,
|
| 23 |
+
"eos_token_id": 50257,
|
| 24 |
+
"forced_decoder_ids": null,
|
| 25 |
+
"init_std": 0.02,
|
| 26 |
+
"is_encoder_decoder": true,
|
| 27 |
+
"mask_feature_length": 10,
|
| 28 |
+
"mask_feature_min_masks": 0,
|
| 29 |
+
"mask_feature_prob": 0.0,
|
| 30 |
+
"mask_time_length": 10,
|
| 31 |
+
"mask_time_min_masks": 2,
|
| 32 |
+
"mask_time_prob": 0.05,
|
| 33 |
+
"max_length": null,
|
| 34 |
+
"max_source_positions": 1500,
|
| 35 |
+
"max_target_positions": 448,
|
| 36 |
+
"median_filter_width": 7,
|
| 37 |
+
"model_type": "whisper",
|
| 38 |
+
"num_hidden_layers": 6,
|
| 39 |
+
"num_mel_bins": 80,
|
| 40 |
+
"pad_token_id": 50257,
|
| 41 |
+
"scale_embedding": false,
|
| 42 |
+
"torch_dtype": "float32",
|
| 43 |
+
"transformers_version": "4.51.3",
|
| 44 |
+
"use_cache": false,
|
| 45 |
+
"use_weighted_layer_sum": false,
|
| 46 |
+
"vocab_size": 51865
|
| 47 |
+
}
|
checkpoint-3686/generation_config.json
ADDED
|
@@ -0,0 +1,159 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alignment_heads": [
|
| 3 |
+
[
|
| 4 |
+
3,
|
| 5 |
+
1
|
| 6 |
+
],
|
| 7 |
+
[
|
| 8 |
+
4,
|
| 9 |
+
2
|
| 10 |
+
],
|
| 11 |
+
[
|
| 12 |
+
4,
|
| 13 |
+
3
|
| 14 |
+
],
|
| 15 |
+
[
|
| 16 |
+
4,
|
| 17 |
+
7
|
| 18 |
+
],
|
| 19 |
+
[
|
| 20 |
+
5,
|
| 21 |
+
1
|
| 22 |
+
],
|
| 23 |
+
[
|
| 24 |
+
5,
|
| 25 |
+
2
|
| 26 |
+
],
|
| 27 |
+
[
|
| 28 |
+
5,
|
| 29 |
+
4
|
| 30 |
+
],
|
| 31 |
+
[
|
| 32 |
+
5,
|
| 33 |
+
6
|
| 34 |
+
]
|
| 35 |
+
],
|
| 36 |
+
"begin_suppress_tokens": [
|
| 37 |
+
220,
|
| 38 |
+
50257
|
| 39 |
+
],
|
| 40 |
+
"bos_token_id": 50257,
|
| 41 |
+
"decoder_start_token_id": 50258,
|
| 42 |
+
"eos_token_id": 50257,
|
| 43 |
+
"is_multilingual": true,
|
| 44 |
+
"lang_to_id": {
|
| 45 |
+
"<|af|>": 50327,
|
| 46 |
+
"<|am|>": 50334,
|
| 47 |
+
"<|ar|>": 50272,
|
| 48 |
+
"<|as|>": 50350,
|
| 49 |
+
"<|az|>": 50304,
|
| 50 |
+
"<|ba|>": 50355,
|
| 51 |
+
"<|be|>": 50330,
|
| 52 |
+
"<|bg|>": 50292,
|
| 53 |
+
"<|bn|>": 50302,
|
| 54 |
+
"<|bo|>": 50347,
|
| 55 |
+
"<|br|>": 50309,
|
| 56 |
+
"<|bs|>": 50315,
|
| 57 |
+
"<|ca|>": 50270,
|
| 58 |
+
"<|cs|>": 50283,
|
| 59 |
+
"<|cy|>": 50297,
|
| 60 |
+
"<|da|>": 50285,
|
| 61 |
+
"<|de|>": 50261,
|
| 62 |
+
"<|el|>": 50281,
|
| 63 |
+
"<|en|>": 50259,
|
| 64 |
+
"<|es|>": 50262,
|
| 65 |
+
"<|et|>": 50307,
|
| 66 |
+
"<|eu|>": 50310,
|
| 67 |
+
"<|fa|>": 50300,
|
| 68 |
+
"<|fi|>": 50277,
|
| 69 |
+
"<|fo|>": 50338,
|
| 70 |
+
"<|fr|>": 50265,
|
| 71 |
+
"<|gl|>": 50319,
|
| 72 |
+
"<|gu|>": 50333,
|
| 73 |
+
"<|haw|>": 50352,
|
| 74 |
+
"<|ha|>": 50354,
|
| 75 |
+
"<|he|>": 50279,
|
| 76 |
+
"<|hi|>": 50276,
|
| 77 |
+
"<|hr|>": 50291,
|
| 78 |
+
"<|ht|>": 50339,
|
| 79 |
+
"<|hu|>": 50286,
|
| 80 |
+
"<|hy|>": 50312,
|
| 81 |
+
"<|id|>": 50275,
|
| 82 |
+
"<|is|>": 50311,
|
| 83 |
+
"<|it|>": 50274,
|
| 84 |
+
"<|ja|>": 50266,
|
| 85 |
+
"<|jw|>": 50356,
|
| 86 |
+
"<|ka|>": 50329,
|
| 87 |
+
"<|kk|>": 50316,
|
| 88 |
+
"<|km|>": 50323,
|
| 89 |
+
"<|kn|>": 50306,
|
| 90 |
+
"<|ko|>": 50264,
|
| 91 |
+
"<|la|>": 50294,
|
| 92 |
+
"<|lb|>": 50345,
|
| 93 |
+
"<|ln|>": 50353,
|
| 94 |
+
"<|lo|>": 50336,
|
| 95 |
+
"<|lt|>": 50293,
|
| 96 |
+
"<|lv|>": 50301,
|
| 97 |
+
"<|mg|>": 50349,
|
| 98 |
+
"<|mi|>": 50295,
|
| 99 |
+
"<|mk|>": 50308,
|
| 100 |
+
"<|ml|>": 50296,
|
| 101 |
+
"<|mn|>": 50314,
|
| 102 |
+
"<|mr|>": 50320,
|
| 103 |
+
"<|ms|>": 50282,
|
| 104 |
+
"<|mt|>": 50343,
|
| 105 |
+
"<|my|>": 50346,
|
| 106 |
+
"<|ne|>": 50313,
|
| 107 |
+
"<|nl|>": 50271,
|
| 108 |
+
"<|nn|>": 50342,
|
| 109 |
+
"<|no|>": 50288,
|
| 110 |
+
"<|oc|>": 50328,
|
| 111 |
+
"<|pa|>": 50321,
|
| 112 |
+
"<|pl|>": 50269,
|
| 113 |
+
"<|ps|>": 50340,
|
| 114 |
+
"<|pt|>": 50267,
|
| 115 |
+
"<|ro|>": 50284,
|
| 116 |
+
"<|ru|>": 50263,
|
| 117 |
+
"<|sa|>": 50344,
|
| 118 |
+
"<|sd|>": 50332,
|
| 119 |
+
"<|si|>": 50322,
|
| 120 |
+
"<|sk|>": 50298,
|
| 121 |
+
"<|sl|>": 50305,
|
| 122 |
+
"<|sn|>": 50324,
|
| 123 |
+
"<|so|>": 50326,
|
| 124 |
+
"<|sq|>": 50317,
|
| 125 |
+
"<|sr|>": 50303,
|
| 126 |
+
"<|su|>": 50357,
|
| 127 |
+
"<|sv|>": 50273,
|
| 128 |
+
"<|sw|>": 50318,
|
| 129 |
+
"<|ta|>": 50287,
|
| 130 |
+
"<|te|>": 50299,
|
| 131 |
+
"<|tg|>": 50331,
|
| 132 |
+
"<|th|>": 50289,
|
| 133 |
+
"<|tk|>": 50341,
|
| 134 |
+
"<|tl|>": 50348,
|
| 135 |
+
"<|tr|>": 50268,
|
| 136 |
+
"<|tt|>": 50351,
|
| 137 |
+
"<|uk|>": 50280,
|
| 138 |
+
"<|ur|>": 50290,
|
| 139 |
+
"<|uz|>": 50337,
|
| 140 |
+
"<|vi|>": 50278,
|
| 141 |
+
"<|yi|>": 50335,
|
| 142 |
+
"<|yo|>": 50325,
|
| 143 |
+
"<|zh|>": 50260
|
| 144 |
+
},
|
| 145 |
+
"language": "ar",
|
| 146 |
+
"max_initial_timestamp_index": 50,
|
| 147 |
+
"max_length": 448,
|
| 148 |
+
"no_timestamps_token_id": 50363,
|
| 149 |
+
"pad_token_id": 50257,
|
| 150 |
+
"prev_sot_token_id": 50361,
|
| 151 |
+
"return_timestamps": false,
|
| 152 |
+
"suppress_tokens": [],
|
| 153 |
+
"task": "transcribe",
|
| 154 |
+
"task_to_id": {
|
| 155 |
+
"transcribe": 50359,
|
| 156 |
+
"translate": 50358
|
| 157 |
+
},
|
| 158 |
+
"transformers_version": "4.51.3"
|
| 159 |
+
}
|
checkpoint-3686/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25c5380fd2de16c27d187fb318eb5131d44d79d42abeda1bd028e84b2ba2bf9f
|
| 3 |
+
size 290403936
|
checkpoint-3686/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba5a0b12275debf8d387024de6a2a1e30753e19f9770e6f8a261e9a848904de3
|
| 3 |
+
size 574811514
|
checkpoint-3686/preprocessor_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"dither": 0.0,
|
| 4 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 5 |
+
"feature_size": 80,
|
| 6 |
+
"hop_length": 160,
|
| 7 |
+
"n_fft": 400,
|
| 8 |
+
"n_samples": 480000,
|
| 9 |
+
"nb_max_frames": 3000,
|
| 10 |
+
"padding_side": "right",
|
| 11 |
+
"padding_value": 0.0,
|
| 12 |
+
"processor_class": "WhisperProcessor",
|
| 13 |
+
"return_attention_mask": false,
|
| 14 |
+
"sampling_rate": 16000
|
| 15 |
+
}
|
checkpoint-3686/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d9c387f74fb135155efad5003e68b3de96bec9ca470019565fd9bb370f86156
|
| 3 |
+
size 14244
|
checkpoint-3686/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:133d9cdff55ea5d96b17cf983bf1c28c4f391f37d78fec884af4d5a91125e100
|
| 3 |
+
size 1064
|
checkpoint-3686/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-3686/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6a097a30b605de118e61115e56bb9d1901b30a5a9f5c370847cf0ec0c0b9a23
|
| 3 |
+
size 5624
|