./outs
Browse files- README.md +11 -11
- config.json +4 -4
- model.safetensors +2 -2
- runs/Oct08_22-05-54_ab5162ac8a56/events.out.tfevents.1728425155.ab5162ac8a56.827.0 +3 -0
- tokenizer_config.json +2 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
-
license:
|
4 |
-
base_model: biodatlab/whisper-th-small
|
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/whisper-th-small
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
-
- Cer: 22.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -37,26 +37,26 @@ More information needed
|
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
- learning_rate: 8e-05
|
40 |
-
- train_batch_size:
|
41 |
- eval_batch_size: 2
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
-
- num_epochs:
|
46 |
- mixed_precision_training: Native AMP
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
52 |
-
| 0.
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
|
56 |
|
57 |
### Framework versions
|
58 |
|
59 |
- Transformers 4.44.2
|
60 |
- Pytorch 2.4.1+cu121
|
61 |
-
- Datasets 3.0.
|
62 |
- Tokenizers 0.19.1
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
license: mit
|
4 |
+
base_model: biodatlab/distill-whisper-th-small
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
model-index:
|
|
|
14 |
|
15 |
# outs
|
16 |
|
17 |
+
This model is a fine-tuned version of [biodatlab/distill-whisper-th-small](https://huggingface.co/biodatlab/distill-whisper-th-small) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.5794
|
20 |
+
- Cer: 22.7354
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
- learning_rate: 8e-05
|
40 |
+
- train_batch_size: 4
|
41 |
- eval_batch_size: 2
|
42 |
- seed: 42
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
+
- num_epochs: 6.0
|
46 |
- mixed_precision_training: Native AMP
|
47 |
|
48 |
### Training results
|
49 |
|
50 |
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
51 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
52 |
+
| 0.3046 | 1.0 | 537 | 0.5714 | 37.0843 |
|
53 |
+
| 0.1192 | 2.0 | 1074 | 0.5905 | 29.1700 |
|
54 |
+
| 0.0471 | 3.0 | 1611 | 0.5794 | 22.7354 |
|
55 |
|
56 |
|
57 |
### Framework versions
|
58 |
|
59 |
- Transformers 4.44.2
|
60 |
- Pytorch 2.4.1+cu121
|
61 |
+
- Datasets 3.0.1
|
62 |
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "biodatlab/whisper-th-small
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": true,
|
@@ -17,7 +17,7 @@
|
|
17 |
"decoder_attention_heads": 12,
|
18 |
"decoder_ffn_dim": 3072,
|
19 |
"decoder_layerdrop": 0.0,
|
20 |
-
"decoder_layers":
|
21 |
"decoder_start_token_id": 50258,
|
22 |
"dropout": 0.0,
|
23 |
"encoder_attention_heads": 12,
|
@@ -30,10 +30,10 @@
|
|
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,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "biodatlab/distill-whisper-th-small",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": true,
|
|
|
17 |
"decoder_attention_heads": 12,
|
18 |
"decoder_ffn_dim": 3072,
|
19 |
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 4,
|
21 |
"decoder_start_token_id": 50258,
|
22 |
"dropout": 0.0,
|
23 |
"encoder_attention_heads": 12,
|
|
|
30 |
"is_encoder_decoder": true,
|
31 |
"mask_feature_length": 64,
|
32 |
"mask_feature_min_masks": 0,
|
33 |
+
"mask_feature_prob": 1e-05,
|
34 |
"mask_time_length": 10,
|
35 |
"mask_time_min_masks": 2,
|
36 |
+
"mask_time_prob": 1e-05,
|
37 |
"max_length": 448,
|
38 |
"max_source_positions": 1500,
|
39 |
"max_target_positions": 448,
|
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:cce52bbee5aaeec31aa652ec967274a497b0c3b5b4c3e60dc9d7632c97cafc0f
|
3 |
+
size 664564920
|
runs/Oct08_22-05-54_ab5162ac8a56/events.out.tfevents.1728425155.ab5162ac8a56.827.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:148a8f0df00a5e6ce1a93542e02b0f75ba0d101f4e7c44684b971c667cc8c62b
|
3 |
+
size 10372
|
tokenizer_config.json
CHANGED
@@ -12985,5 +12985,6 @@
|
|
12985 |
"processor_class": "WhisperProcessor",
|
12986 |
"return_attention_mask": false,
|
12987 |
"tokenizer_class": "WhisperTokenizer",
|
12988 |
-
"unk_token": "<|endoftext|>"
|
|
|
12989 |
}
|
|
|
12985 |
"processor_class": "WhisperProcessor",
|
12986 |
"return_attention_mask": false,
|
12987 |
"tokenizer_class": "WhisperTokenizer",
|
12988 |
+
"unk_token": "<|endoftext|>",
|
12989 |
+
"use_fast": true
|
12990 |
}
|
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 sha256:88ddf1d9023ed0d0a44a60aab42edf6a7bb32fd900ce380a63a0d73798e2e5f5
|
3 |
size 5304
|