Commit
·
cdec6ef
1
Parent(s):
de710f7
Training in progress, step 300
Browse files- .gitignore +1 -0
- config.json +42 -0
- preprocessor_config.json +0 -0
- pytorch_model.bin +3 -0
- runs/Mar17_05-04-43_3422217a042b/1742188018.4191842/events.out.tfevents.1742188018.3422217a042b.200.1 +3 -0
- runs/Mar17_05-04-43_3422217a042b/events.out.tfevents.1742188018.3422217a042b.200.0 +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-tiny-mn-9",
|
| 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": 384,
|
| 15 |
+
"decoder_attention_heads": 6,
|
| 16 |
+
"decoder_ffn_dim": 1536,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 4,
|
| 19 |
+
"decoder_start_token_id": 50258,
|
| 20 |
+
"dropout": 0.0,
|
| 21 |
+
"encoder_attention_heads": 6,
|
| 22 |
+
"encoder_ffn_dim": 1536,
|
| 23 |
+
"encoder_layerdrop": 0.0,
|
| 24 |
+
"encoder_layers": 4,
|
| 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": 4,
|
| 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 sha256:3cd40bbf6576cdd02a346610fe504de6a367418d6bb649ff08ac6adb2ff63b70
|
| 3 |
+
size 151099430
|
runs/Mar17_05-04-43_3422217a042b/1742188018.4191842/events.out.tfevents.1742188018.3422217a042b.200.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17e5543de632930ceffb2a65218744aa15f81dcdc749f272f10f35bb618acda6
|
| 3 |
+
size 5973
|
runs/Mar17_05-04-43_3422217a042b/events.out.tfevents.1742188018.3422217a042b.200.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3159122cc2e40b6b27c7ec553e86f7b2beec67168eb19fdb88477b090dd97968
|
| 3 |
+
size 6579
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c1666ad1576b71db70fca7da7f0e2ad63919d63a55d67de172a315b5bcc1b62
|
| 3 |
+
size 4088
|