Otgonbaatar
commited on
Commit
·
72d34e0
1
Parent(s):
3feae99
Training in progress, step 3
Browse files- .gitignore +1 -0
- config.json +42 -0
- preprocessor_config.json +0 -0
- pytorch_model.bin +3 -0
- runs/Dec23_03-28-04_df0c5f05b1a9/1734924505.7462282/events.out.tfevents.1734924505.df0c5f05b1a9.47236.1 +3 -0
- runs/Dec23_03-28-04_df0c5f05b1a9/events.out.tfevents.1734924505.df0c5f05b1a9.47236.0 +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bayartsogt/whisper-small-mn-8",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"architectures": [
|
6 |
+
"WhisperForConditionalGeneration"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
+
"begin_suppress_tokens": [
|
10 |
+
220,
|
11 |
+
50257
|
12 |
+
],
|
13 |
+
"bos_token_id": 50257,
|
14 |
+
"d_model": 768,
|
15 |
+
"decoder_attention_heads": 12,
|
16 |
+
"decoder_ffn_dim": 3072,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 12,
|
19 |
+
"decoder_start_token_id": 50258,
|
20 |
+
"dropout": 0.0,
|
21 |
+
"encoder_attention_heads": 12,
|
22 |
+
"encoder_ffn_dim": 3072,
|
23 |
+
"encoder_layerdrop": 0.0,
|
24 |
+
"encoder_layers": 12,
|
25 |
+
"eos_token_id": 50257,
|
26 |
+
"forced_decoder_ids": null,
|
27 |
+
"init_std": 0.02,
|
28 |
+
"is_encoder_decoder": true,
|
29 |
+
"max_length": 448,
|
30 |
+
"max_source_positions": 1500,
|
31 |
+
"max_target_positions": 448,
|
32 |
+
"model_type": "whisper",
|
33 |
+
"num_hidden_layers": 12,
|
34 |
+
"num_mel_bins": 80,
|
35 |
+
"pad_token_id": 50257,
|
36 |
+
"scale_embedding": false,
|
37 |
+
"suppress_tokens": [],
|
38 |
+
"torch_dtype": "float32",
|
39 |
+
"transformers_version": "4.26.0",
|
40 |
+
"use_cache": false,
|
41 |
+
"vocab_size": 51865
|
42 |
+
}
|
preprocessor_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f71a5d2a057ffe80b1f148bcdc85fbb13cba4f1ecbfa8450d5b4c3e81bf5e75
|
3 |
+
size 967103046
|
runs/Dec23_03-28-04_df0c5f05b1a9/1734924505.7462282/events.out.tfevents.1734924505.df0c5f05b1a9.47236.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c7b439f89495024f147bb4c0a47b3a6c58e98d5caff8df44b2fe48ab1fac74d
|
3 |
+
size 5976
|
runs/Dec23_03-28-04_df0c5f05b1a9/events.out.tfevents.1734924505.df0c5f05b1a9.47236.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b95f2f14ca62a136619ce7a2334ba60de33990f04642190e2d6471b5b36e07cb
|
3 |
+
size 4705
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ff213277f686c8fffeba8ad96f212a3832062b7d82e71b942c8464d6eeee6e5
|
3 |
+
size 4088
|