Training in progress, epoch 1
Browse files
config.json
ADDED
@@ -0,0 +1,66 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "yaygomii/whisper-small-ta-fyp",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"apply_spec_augment": false,
|
6 |
+
"architectures": [
|
7 |
+
"WhisperForAudioClassification"
|
8 |
+
],
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"begin_suppress_tokens": [
|
11 |
+
220,
|
12 |
+
50257
|
13 |
+
],
|
14 |
+
"bos_token_id": 50257,
|
15 |
+
"classifier_proj_size": 256,
|
16 |
+
"d_model": 768,
|
17 |
+
"decoder_attention_heads": 12,
|
18 |
+
"decoder_ffn_dim": 3072,
|
19 |
+
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 12,
|
21 |
+
"decoder_start_token_id": 50258,
|
22 |
+
"dropout": 0.0,
|
23 |
+
"encoder_attention_heads": 12,
|
24 |
+
"encoder_ffn_dim": 3072,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 12,
|
27 |
+
"eos_token_id": 50257,
|
28 |
+
"forced_decoder_ids": null,
|
29 |
+
"id2label": {
|
30 |
+
"0": "Central_Dialect",
|
31 |
+
"1": "Northern_Dialect",
|
32 |
+
"2": "Southern_Dialect",
|
33 |
+
"3": "Western_Dialect",
|
34 |
+
"4": "Brahmin_Dialect"
|
35 |
+
},
|
36 |
+
"init_std": 0.02,
|
37 |
+
"is_encoder_decoder": true,
|
38 |
+
"label2id": {
|
39 |
+
"Brahmin_Dialect": "4",
|
40 |
+
"Central_Dialect": "0",
|
41 |
+
"Northern_Dialect": "1",
|
42 |
+
"Southern_Dialect": "2",
|
43 |
+
"Western_Dialect": "3"
|
44 |
+
},
|
45 |
+
"mask_feature_length": 10,
|
46 |
+
"mask_feature_min_masks": 0,
|
47 |
+
"mask_feature_prob": 0.0,
|
48 |
+
"mask_time_length": 10,
|
49 |
+
"mask_time_min_masks": 2,
|
50 |
+
"mask_time_prob": 0.05,
|
51 |
+
"max_length": 448,
|
52 |
+
"max_source_positions": 1500,
|
53 |
+
"max_target_positions": 448,
|
54 |
+
"median_filter_width": 7,
|
55 |
+
"model_type": "whisper",
|
56 |
+
"num_hidden_layers": 12,
|
57 |
+
"num_mel_bins": 80,
|
58 |
+
"pad_token_id": 50257,
|
59 |
+
"scale_embedding": false,
|
60 |
+
"suppress_tokens": [],
|
61 |
+
"torch_dtype": "float32",
|
62 |
+
"transformers_version": "4.40.0.dev0",
|
63 |
+
"use_cache": true,
|
64 |
+
"use_weighted_layer_sum": false,
|
65 |
+
"vocab_size": 51865
|
66 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af3d53aae6b47956c6bea805a9274bfe50e0414ce5509801f0497cbe7ca17787
|
3 |
+
size 353429444
|
preprocessor_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"chunk_length": 30,
|
3 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
4 |
+
"feature_size": 80,
|
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 |
+
}
|
runs/Apr08_04-03-59_d7a4a8e161e6/events.out.tfevents.1712549056.d7a4a8e161e6.1457.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48ac38324e51953001fd2d61812694985c9b5100315d148405356ba48eb7d749
|
3 |
+
size 28736
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b4b1bd45df27f25f0d04dcc4f4c27b13ed39f1b74ffdd4f8b9eb8b41bae4501b
|
3 |
+
size 5048
|