Training in progress, step 500
Browse files- README.md +0 -61
- config.json +7 -0
- generation_config.json +0 -4
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
README.md
DELETED
@@ -1,61 +0,0 @@
|
|
1 |
-
---
|
2 |
-
license: apache-2.0
|
3 |
-
tags:
|
4 |
-
- generated_from_trainer
|
5 |
-
datasets:
|
6 |
-
- 10th_science_tamil_to_english
|
7 |
-
model-index:
|
8 |
-
- name: 10th_science_ta_to_eng
|
9 |
-
results: []
|
10 |
-
---
|
11 |
-
|
12 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
-
should probably proofread and complete it, then remove this comment. -->
|
14 |
-
|
15 |
-
# 10th_science_ta_to_eng
|
16 |
-
|
17 |
-
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the 10th_science_tamil_to_english dataset.
|
18 |
-
It achieves the following results on the evaluation set:
|
19 |
-
- eval_loss: 3.0929
|
20 |
-
- eval_wer: 157.7166
|
21 |
-
- eval_runtime: 270.5806
|
22 |
-
- eval_samples_per_second: 1.434
|
23 |
-
- eval_steps_per_second: 0.092
|
24 |
-
- epoch: 13.0
|
25 |
-
- step: 500
|
26 |
-
|
27 |
-
## Model description
|
28 |
-
|
29 |
-
More information needed
|
30 |
-
|
31 |
-
## Intended uses & limitations
|
32 |
-
|
33 |
-
More information needed
|
34 |
-
|
35 |
-
## Training and evaluation data
|
36 |
-
|
37 |
-
More information needed
|
38 |
-
|
39 |
-
## Training procedure
|
40 |
-
|
41 |
-
### Training hyperparameters
|
42 |
-
|
43 |
-
The following hyperparameters were used during training:
|
44 |
-
- learning_rate: 1e-05
|
45 |
-
- train_batch_size: 32
|
46 |
-
- eval_batch_size: 16
|
47 |
-
- seed: 42
|
48 |
-
- gradient_accumulation_steps: 2
|
49 |
-
- total_train_batch_size: 64
|
50 |
-
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
-
- lr_scheduler_type: linear
|
52 |
-
- lr_scheduler_warmup_steps: 500
|
53 |
-
- training_steps: 5000
|
54 |
-
- mixed_precision_training: Native AMP
|
55 |
-
|
56 |
-
### Framework versions
|
57 |
-
|
58 |
-
- Transformers 4.27.0.dev0
|
59 |
-
- Pytorch 1.13.1+cu116
|
60 |
-
- Datasets 2.10.1.dev0
|
61 |
-
- Tokenizers 0.13.2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
CHANGED
@@ -2,6 +2,7 @@
|
|
2 |
"_name_or_path": "openai/whisper-base",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
|
|
5 |
"architectures": [
|
6 |
"WhisperForConditionalGeneration"
|
7 |
],
|
@@ -26,6 +27,12 @@
|
|
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,
|
|
|
2 |
"_name_or_path": "openai/whisper-base",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
+
"apply_spec_augment": false,
|
6 |
"architectures": [
|
7 |
"WhisperForConditionalGeneration"
|
8 |
],
|
|
|
27 |
"forced_decoder_ids": null,
|
28 |
"init_std": 0.02,
|
29 |
"is_encoder_decoder": true,
|
30 |
+
"mask_feature_length": 10,
|
31 |
+
"mask_feature_min_masks": 0,
|
32 |
+
"mask_feature_prob": 0.0,
|
33 |
+
"mask_time_length": 10,
|
34 |
+
"mask_time_min_masks": 2,
|
35 |
+
"mask_time_prob": 0.05,
|
36 |
"max_length": 448,
|
37 |
"max_source_positions": 1500,
|
38 |
"max_target_positions": 448,
|
generation_config.json
CHANGED
@@ -14,10 +14,6 @@
|
|
14 |
[
|
15 |
2,
|
16 |
50359
|
17 |
-
],
|
18 |
-
[
|
19 |
-
3,
|
20 |
-
50363
|
21 |
]
|
22 |
],
|
23 |
"is_multilingual": true,
|
|
|
14 |
[
|
15 |
2,
|
16 |
50359
|
|
|
|
|
|
|
|
|
17 |
]
|
18 |
],
|
19 |
"is_multilingual": true,
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 290458721
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3bc702d51c5eb4393d61ea4995a797b151c2df2abd21ceb7c0ebedb33e2e67f7
|
3 |
size 290458721
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3707
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fd04f7e3e430263127912a8b73d2f63b44c704889d7eed0a1b4c4eac9b87d3f
|
3 |
size 3707
|