rdg-rvc-dev
commited on
Commit
•
09f4646
1
Parent(s):
068f4a1
Training in progress, step 100
Browse files
config.json
CHANGED
@@ -1,52 +1,52 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "openai/whisper-medium",
|
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": [
|
11 |
-
220,
|
12 |
-
50257
|
13 |
-
],
|
14 |
-
"bos_token_id": 50257,
|
15 |
-
"classifier_proj_size": 256,
|
16 |
-
"d_model": 1024,
|
17 |
-
"decoder_attention_heads": 16,
|
18 |
-
"decoder_ffn_dim": 4096,
|
19 |
-
"decoder_layerdrop": 0.0,
|
20 |
-
"decoder_layers": 24,
|
21 |
-
"decoder_start_token_id": 50258,
|
22 |
-
"dropout": 0.0,
|
23 |
-
"encoder_attention_heads": 16,
|
24 |
-
"encoder_ffn_dim": 4096,
|
25 |
-
"encoder_layerdrop": 0.0,
|
26 |
-
"encoder_layers": 24,
|
27 |
-
"eos_token_id": 50257,
|
28 |
-
"forced_decoder_ids": null,
|
29 |
-
"init_std": 0.02,
|
30 |
-
"is_encoder_decoder": true,
|
31 |
-
"mask_feature_length": 10,
|
32 |
-
"mask_feature_min_masks": 0,
|
33 |
-
"mask_feature_prob": 0.0,
|
34 |
-
"mask_time_length": 10,
|
35 |
-
"mask_time_min_masks": 2,
|
36 |
-
"mask_time_prob": 0.05,
|
37 |
-
"max_length": 448,
|
38 |
-
"max_source_positions": 1500,
|
39 |
-
"max_target_positions": 448,
|
40 |
-
"median_filter_width": 7,
|
41 |
-
"model_type": "whisper",
|
42 |
-
"num_hidden_layers": 24,
|
43 |
-
"num_mel_bins": 80,
|
44 |
-
"pad_token_id": 50257,
|
45 |
-
"scale_embedding": false,
|
46 |
-
"suppress_tokens": [],
|
47 |
-
"torch_dtype": "float32",
|
48 |
-
"transformers_version": "4.
|
49 |
-
"use_cache": true,
|
50 |
-
"use_weighted_layer_sum": false,
|
51 |
-
"vocab_size": 51865
|
52 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai/whisper-medium",
|
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": [
|
11 |
+
220,
|
12 |
+
50257
|
13 |
+
],
|
14 |
+
"bos_token_id": 50257,
|
15 |
+
"classifier_proj_size": 256,
|
16 |
+
"d_model": 1024,
|
17 |
+
"decoder_attention_heads": 16,
|
18 |
+
"decoder_ffn_dim": 4096,
|
19 |
+
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 24,
|
21 |
+
"decoder_start_token_id": 50258,
|
22 |
+
"dropout": 0.0,
|
23 |
+
"encoder_attention_heads": 16,
|
24 |
+
"encoder_ffn_dim": 4096,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 24,
|
27 |
+
"eos_token_id": 50257,
|
28 |
+
"forced_decoder_ids": null,
|
29 |
+
"init_std": 0.02,
|
30 |
+
"is_encoder_decoder": true,
|
31 |
+
"mask_feature_length": 10,
|
32 |
+
"mask_feature_min_masks": 0,
|
33 |
+
"mask_feature_prob": 0.0,
|
34 |
+
"mask_time_length": 10,
|
35 |
+
"mask_time_min_masks": 2,
|
36 |
+
"mask_time_prob": 0.05,
|
37 |
+
"max_length": 448,
|
38 |
+
"max_source_positions": 1500,
|
39 |
+
"max_target_positions": 448,
|
40 |
+
"median_filter_width": 7,
|
41 |
+
"model_type": "whisper",
|
42 |
+
"num_hidden_layers": 24,
|
43 |
+
"num_mel_bins": 80,
|
44 |
+
"pad_token_id": 50257,
|
45 |
+
"scale_embedding": false,
|
46 |
+
"suppress_tokens": [],
|
47 |
+
"torch_dtype": "float32",
|
48 |
+
"transformers_version": "4.42.3",
|
49 |
+
"use_cache": true,
|
50 |
+
"use_weighted_layer_sum": false,
|
51 |
+
"vocab_size": 51865
|
52 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3055544304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65ad9a75f1bcfd14cb2410dc615397dfda09093f38bbe08e55520e03f5ba7828
|
3 |
size 3055544304
|
preprocessor_config.json
CHANGED
@@ -1,14 +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 |
-
}
|
|
|
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/Jul09_21-42-33_DESKTOP-0Q1NC6M/events.out.tfevents.1720572165.DESKTOP-0Q1NC6M.6300.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:732fe6381c3d9dc0c025631c6eb8e22e741d19bed9cc6bde9a29aa0aaa06a474
|
3 |
+
size 6869
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac8f4c4bccc5aa29969a2758e85fb8975642eaa6471b37ebca00e968defa66c4
|
3 |
+
size 5304
|