Training in progress, step 1000
Browse files- config.json +61 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai/whisper-large-v2",
|
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": null,
|
11 |
+
"bos_token_id": 50257,
|
12 |
+
"classifier_proj_size": 256,
|
13 |
+
"d_model": 1280,
|
14 |
+
"decoder_attention_heads": 20,
|
15 |
+
"decoder_ffn_dim": 5120,
|
16 |
+
"decoder_layerdrop": 0.0,
|
17 |
+
"decoder_layers": 32,
|
18 |
+
"decoder_start_token_id": 50258,
|
19 |
+
"dropout": 0.0,
|
20 |
+
"encoder_attention_heads": 20,
|
21 |
+
"encoder_ffn_dim": 5120,
|
22 |
+
"encoder_layerdrop": 0.0,
|
23 |
+
"encoder_layers": 32,
|
24 |
+
"eos_token_id": 50257,
|
25 |
+
"forced_decoder_ids": [
|
26 |
+
[
|
27 |
+
1,
|
28 |
+
50259
|
29 |
+
],
|
30 |
+
[
|
31 |
+
2,
|
32 |
+
50359
|
33 |
+
],
|
34 |
+
[
|
35 |
+
3,
|
36 |
+
50363
|
37 |
+
]
|
38 |
+
],
|
39 |
+
"init_std": 0.02,
|
40 |
+
"is_encoder_decoder": true,
|
41 |
+
"mask_feature_length": 10,
|
42 |
+
"mask_feature_min_masks": 0,
|
43 |
+
"mask_feature_prob": 0.0,
|
44 |
+
"mask_time_length": 10,
|
45 |
+
"mask_time_min_masks": 2,
|
46 |
+
"mask_time_prob": 0.05,
|
47 |
+
"max_length": null,
|
48 |
+
"max_source_positions": 1500,
|
49 |
+
"max_target_positions": 448,
|
50 |
+
"median_filter_width": 7,
|
51 |
+
"model_type": "whisper",
|
52 |
+
"num_hidden_layers": 32,
|
53 |
+
"num_mel_bins": 80,
|
54 |
+
"pad_token_id": 50257,
|
55 |
+
"scale_embedding": false,
|
56 |
+
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.45.2",
|
58 |
+
"use_cache": false,
|
59 |
+
"use_weighted_layer_sum": false,
|
60 |
+
"vocab_size": 51865
|
61 |
+
}
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:424b8aad4e728e8424b6538245d1f696f45b4bd64802ea02a5d8fad929ab2124
|
3 |
+
size 4992706480
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cea20e34d2d86900ec64db099d291b1009edcf6365968e2dd2438c16de9a7a0e
|
3 |
+
size 1180663192
|
model.safetensors.index.json
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 sha256:9cf0d2237eeb856a921f724b0f5d10e059228fb0e7a32b92878960b027de85da
|
3 |
+
size 5368
|