Commit
•
2e1dabb
1
Parent(s):
58023bf
End of training
Browse files- README.md +14 -14
- config.json +9 -9
- generation_config.json +23 -15
- model.safetensors +2 -2
- runs/Jun09_02-20-59_cxrocket-SERVER/events.out.tfevents.1717896060.cxrocket-SERVER.218772.0 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -2,11 +2,11 @@
|
|
2 |
language:
|
3 |
- ar
|
4 |
license: apache-2.0
|
5 |
-
base_model: openai/whisper-
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
-
- Arbi-Houssem/Tunisian_dataset_STT-
|
10 |
metrics:
|
11 |
- wer
|
12 |
model-index:
|
@@ -16,13 +16,13 @@ model-index:
|
|
16 |
name: Automatic Speech Recognition
|
17 |
type: automatic-speech-recognition
|
18 |
dataset:
|
19 |
-
name: Tunisian_dataset_STT-
|
20 |
-
type: Arbi-Houssem/Tunisian_dataset_STT-
|
21 |
args: 'config: ar, split: test'
|
22 |
metrics:
|
23 |
- name: Wer
|
24 |
type: wer
|
25 |
-
value:
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -30,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
30 |
|
31 |
# Whisper Tunisien
|
32 |
|
33 |
-
This model is a fine-tuned version of [openai/whisper-
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss:
|
36 |
-
- Wer:
|
37 |
|
38 |
## Model description
|
39 |
|
@@ -52,8 +52,8 @@ More information needed
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
-
- learning_rate: 1e-
|
56 |
-
- train_batch_size:
|
57 |
- eval_batch_size: 16
|
58 |
- seed: 42
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
@@ -66,10 +66,10 @@ The following hyperparameters were used during training:
|
|
66 |
|
67 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
68 |
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
|
74 |
|
75 |
### Framework versions
|
|
|
2 |
language:
|
3 |
- ar
|
4 |
license: apache-2.0
|
5 |
+
base_model: openai/whisper-small
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
+
- Arbi-Houssem/Tunisian_dataset_STT-TTS1
|
10 |
metrics:
|
11 |
- wer
|
12 |
model-index:
|
|
|
16 |
name: Automatic Speech Recognition
|
17 |
type: automatic-speech-recognition
|
18 |
dataset:
|
19 |
+
name: Tunisian_dataset_STT-TTS1
|
20 |
+
type: Arbi-Houssem/Tunisian_dataset_STT-TTS1
|
21 |
args: 'config: ar, split: test'
|
22 |
metrics:
|
23 |
- name: Wer
|
24 |
type: wer
|
25 |
+
value: 99.41634241245137
|
26 |
---
|
27 |
|
28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
30 |
|
31 |
# Whisper Tunisien
|
32 |
|
33 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Tunisian_dataset_STT-TTS1 dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 2.9262
|
36 |
+
- Wer: 99.4163
|
37 |
|
38 |
## Model description
|
39 |
|
|
|
52 |
### Training hyperparameters
|
53 |
|
54 |
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 1e-06
|
56 |
+
- train_batch_size: 8
|
57 |
- eval_batch_size: 16
|
58 |
- seed: 42
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
|
66 |
|
67 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
68 |
|:-------------:|:-------:|:----:|:---------------:|:--------:|
|
69 |
+
| 0.565 | 10.3093 | 1000 | 2.7181 | 99.5460 |
|
70 |
+
| 0.2875 | 20.6186 | 2000 | 2.7486 | 106.3554 |
|
71 |
+
| 0.1701 | 30.9278 | 3000 | 2.8744 | 103.2425 |
|
72 |
+
| 0.1375 | 41.2371 | 4000 | 2.9262 | 99.4163 |
|
73 |
|
74 |
|
75 |
### Framework versions
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "openai/whisper-
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": false,
|
@@ -13,17 +13,17 @@
|
|
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,
|
@@ -39,7 +39,7 @@
|
|
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": "openai/whisper-small",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": false,
|
|
|
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 |
"init_std": 0.02,
|
|
|
39 |
"max_target_positions": 448,
|
40 |
"median_filter_width": 7,
|
41 |
"model_type": "whisper",
|
42 |
+
"num_hidden_layers": 12,
|
43 |
"num_mel_bins": 80,
|
44 |
"pad_token_id": 50257,
|
45 |
"scale_embedding": false,
|
generation_config.json
CHANGED
@@ -1,36 +1,44 @@
|
|
1 |
{
|
2 |
"alignment_heads": [
|
3 |
[
|
4 |
-
|
5 |
-
|
6 |
],
|
7 |
[
|
8 |
-
|
9 |
-
|
10 |
],
|
11 |
[
|
12 |
-
|
13 |
-
|
14 |
],
|
15 |
[
|
16 |
-
|
|
|
|
|
|
|
|
|
17 |
7
|
18 |
],
|
19 |
[
|
20 |
-
|
21 |
-
|
22 |
],
|
23 |
[
|
24 |
-
|
25 |
-
|
26 |
],
|
27 |
[
|
28 |
-
|
29 |
-
|
30 |
],
|
31 |
[
|
32 |
-
|
33 |
-
|
|
|
|
|
|
|
|
|
34 |
]
|
35 |
],
|
36 |
"begin_suppress_tokens": [
|
|
|
1 |
{
|
2 |
"alignment_heads": [
|
3 |
[
|
4 |
+
5,
|
5 |
+
3
|
6 |
],
|
7 |
[
|
8 |
+
5,
|
9 |
+
9
|
10 |
],
|
11 |
[
|
12 |
+
8,
|
13 |
+
0
|
14 |
],
|
15 |
[
|
16 |
+
8,
|
17 |
+
4
|
18 |
+
],
|
19 |
+
[
|
20 |
+
8,
|
21 |
7
|
22 |
],
|
23 |
[
|
24 |
+
8,
|
25 |
+
8
|
26 |
],
|
27 |
[
|
28 |
+
9,
|
29 |
+
0
|
30 |
],
|
31 |
[
|
32 |
+
9,
|
33 |
+
7
|
34 |
],
|
35 |
[
|
36 |
+
9,
|
37 |
+
9
|
38 |
+
],
|
39 |
+
[
|
40 |
+
10,
|
41 |
+
5
|
42 |
]
|
43 |
],
|
44 |
"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:ece54d87ddf30cc6133edc4510dd41bb73d787158430c61cab6e9427e6521141
|
3 |
+
size 966995080
|
runs/Jun09_02-20-59_cxrocket-SERVER/events.out.tfevents.1717896060.cxrocket-SERVER.218772.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:59fcb9ee8acb8ff198fecca073cd3922a17cfe8aa57fd8f9143d2bbb365357e7
|
3 |
+
size 41074
|
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 sha256:7c8966eba90416ac68c6f5f018f21d8f0770433b71c36d0201111b1c487bbca7
|
3 |
size 5304
|