./outs
Browse files- README.md +8 -8
- config.json +11 -11
- generation_config.json +10 -26
- model.safetensors +2 -2
- runs/Oct08_22-51-00_1f4575752976/events.out.tfevents.1728427864.1f4575752976.965.0 +3 -0
- tokenizer_config.json +1 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
-
license:
|
4 |
-
base_model: biodatlab/
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
@@ -14,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# outs
|
16 |
|
17 |
-
This model is a fine-tuned version of [biodatlab/
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
-
- Cer:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -49,9 +49,9 @@ The following hyperparameters were used during training:
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
|
56 |
|
57 |
### Framework versions
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: biodatlab/whisper-th-medium-combined
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
|
|
14 |
|
15 |
# outs
|
16 |
|
17 |
+
This model is a fine-tuned version of [biodatlab/whisper-th-medium-combined](https://huggingface.co/biodatlab/whisper-th-medium-combined) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.5637
|
20 |
+
- Cer: 29.9814
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
52 |
+
| 0.3375 | 1.0 | 537 | 0.5168 | 24.9036 |
|
53 |
+
| 0.2035 | 2.0 | 1074 | 0.5558 | 28.2356 |
|
54 |
+
| 0.0809 | 3.0 | 1611 | 0.5637 | 29.9814 |
|
55 |
|
56 |
|
57 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "biodatlab/
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": true,
|
@@ -13,33 +13,33 @@
|
|
13 |
],
|
14 |
"bos_token_id": 50257,
|
15 |
"classifier_proj_size": 256,
|
16 |
-
"d_model":
|
17 |
-
"decoder_attention_heads":
|
18 |
-
"decoder_ffn_dim":
|
19 |
"decoder_layerdrop": 0.0,
|
20 |
-
"decoder_layers":
|
21 |
"decoder_start_token_id": 50258,
|
22 |
"dropout": 0.0,
|
23 |
-
"encoder_attention_heads":
|
24 |
-
"encoder_ffn_dim":
|
25 |
"encoder_layerdrop": 0.0,
|
26 |
-
"encoder_layers":
|
27 |
"eos_token_id": 50257,
|
28 |
"forced_decoder_ids": null,
|
29 |
"init_std": 0.02,
|
30 |
"is_encoder_decoder": true,
|
31 |
"mask_feature_length": 64,
|
32 |
"mask_feature_min_masks": 0,
|
33 |
-
"mask_feature_prob":
|
34 |
"mask_time_length": 10,
|
35 |
"mask_time_min_masks": 2,
|
36 |
-
"mask_time_prob":
|
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":
|
43 |
"num_mel_bins": 80,
|
44 |
"pad_token_id": 50257,
|
45 |
"scale_embedding": false,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "biodatlab/whisper-th-medium-combined",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": true,
|
|
|
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": 64,
|
32 |
"mask_feature_min_masks": 0,
|
33 |
+
"mask_feature_prob": 0.1,
|
34 |
"mask_time_length": 10,
|
35 |
"mask_time_min_masks": 2,
|
36 |
+
"mask_time_prob": 0.1,
|
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,
|
generation_config.json
CHANGED
@@ -1,44 +1,28 @@
|
|
1 |
{
|
2 |
"alignment_heads": [
|
3 |
[
|
4 |
-
|
5 |
-
|
6 |
],
|
7 |
[
|
8 |
-
|
9 |
-
9
|
10 |
-
],
|
11 |
-
[
|
12 |
-
8,
|
13 |
-
0
|
14 |
-
],
|
15 |
-
[
|
16 |
-
8,
|
17 |
4
|
18 |
],
|
19 |
[
|
20 |
-
|
21 |
-
|
22 |
],
|
23 |
[
|
24 |
-
|
25 |
-
|
26 |
],
|
27 |
[
|
28 |
-
|
29 |
0
|
30 |
],
|
31 |
[
|
32 |
-
|
33 |
-
|
34 |
-
],
|
35 |
-
[
|
36 |
-
9,
|
37 |
-
9
|
38 |
-
],
|
39 |
-
[
|
40 |
-
10,
|
41 |
-
5
|
42 |
]
|
43 |
],
|
44 |
"begin_suppress_tokens": [
|
|
|
1 |
{
|
2 |
"alignment_heads": [
|
3 |
[
|
4 |
+
13,
|
5 |
+
15
|
6 |
],
|
7 |
[
|
8 |
+
15,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
4
|
10 |
],
|
11 |
[
|
12 |
+
15,
|
13 |
+
15
|
14 |
],
|
15 |
[
|
16 |
+
16,
|
17 |
+
1
|
18 |
],
|
19 |
[
|
20 |
+
20,
|
21 |
0
|
22 |
],
|
23 |
[
|
24 |
+
23,
|
25 |
+
4
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
]
|
27 |
],
|
28 |
"begin_suppress_tokens": [
|
model.safetensors
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:f163cc930ff7ae702cf9db5ea3ecc7ca4d771e708a111ef0a7f6b5fe5eb37b0e
|
3 |
+
size 3055544304
|
runs/Oct08_22-51-00_1f4575752976/events.out.tfevents.1728427864.1f4575752976.965.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6c889b6d7108477c967a9a55b239426a64ff002ed15d86acab598e8752f1a4d
|
3 |
+
size 10372
|
tokenizer_config.json
CHANGED
@@ -12985,6 +12985,5 @@
|
|
12985 |
"processor_class": "WhisperProcessor",
|
12986 |
"return_attention_mask": false,
|
12987 |
"tokenizer_class": "WhisperTokenizer",
|
12988 |
-
"unk_token": "<|endoftext|>"
|
12989 |
-
"use_fast": true
|
12990 |
}
|
|
|
12985 |
"processor_class": "WhisperProcessor",
|
12986 |
"return_attention_mask": false,
|
12987 |
"tokenizer_class": "WhisperTokenizer",
|
12988 |
+
"unk_token": "<|endoftext|>"
|
|
|
12989 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36fd56e536c7d72531cae2b80ea823836ac51b338b4a62138a2a3494649243a4
|
3 |
size 5304
|