Commit
•
5f8d76d
1
Parent(s):
518546f
End of training
Browse files- README.md +85 -0
- config.json +65 -0
- generation_config.json +28 -0
- model.safetensors +3 -0
- preprocessor_config.json +14 -0
- runs/May09_17-56-05_70784b0afc4f/events.out.tfevents.1715277375.70784b0afc4f.181.0 +3 -0
- runs/May09_18-26-37_70784b0afc4f/events.out.tfevents.1715279208.70784b0afc4f.181.1 +3 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- ar
|
4 |
+
license: apache-2.0
|
5 |
+
base_model: tarteel-ai/whisper-base-ar-quran
|
6 |
+
tags:
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- mozilla-foundation/common_voice_11_0
|
10 |
+
metrics:
|
11 |
+
- wer
|
12 |
+
model-index:
|
13 |
+
- name: Whisper Small Ar - raghad
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Automatic Speech Recognition
|
17 |
+
type: automatic-speech-recognition
|
18 |
+
dataset:
|
19 |
+
name: Zolfa Dataset
|
20 |
+
type: mozilla-foundation/common_voice_11_0
|
21 |
+
args: 'config: ar, split: test'
|
22 |
+
metrics:
|
23 |
+
- name: Wer
|
24 |
+
type: wer
|
25 |
+
value: 10.344827586206897
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# Whisper Small Ar - raghad
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [tarteel-ai/whisper-base-ar-quran](https://huggingface.co/tarteel-ai/whisper-base-ar-quran) on the Zolfa Dataset dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.0195
|
36 |
+
- Wer: 10.3448
|
37 |
+
|
38 |
+
## Model description
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Intended uses & limitations
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training and evaluation data
|
47 |
+
|
48 |
+
More information needed
|
49 |
+
|
50 |
+
## Training procedure
|
51 |
+
|
52 |
+
### Training hyperparameters
|
53 |
+
|
54 |
+
The following hyperparameters were used during training:
|
55 |
+
- learning_rate: 1e-05
|
56 |
+
- train_batch_size: 16
|
57 |
+
- eval_batch_size: 2
|
58 |
+
- seed: 42
|
59 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
+
- lr_scheduler_type: linear
|
61 |
+
- num_epochs: 10
|
62 |
+
- mixed_precision_training: Native AMP
|
63 |
+
|
64 |
+
### Training results
|
65 |
+
|
66 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
67 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
68 |
+
| 0.0045 | 1.0 | 21 | 0.0047 | 0.0 |
|
69 |
+
| 0.0015 | 2.0 | 42 | 0.0220 | 10.3448 |
|
70 |
+
| 0.0012 | 3.0 | 63 | 0.0223 | 10.3448 |
|
71 |
+
| 0.0006 | 4.0 | 84 | 0.0161 | 10.3448 |
|
72 |
+
| 0.0004 | 5.0 | 105 | 0.0199 | 10.3448 |
|
73 |
+
| 0.0003 | 6.0 | 126 | 0.0187 | 10.3448 |
|
74 |
+
| 0.0002 | 7.0 | 147 | 0.0181 | 10.3448 |
|
75 |
+
| 0.0003 | 8.0 | 168 | 0.0195 | 10.3448 |
|
76 |
+
| 0.0002 | 9.0 | 189 | 0.0193 | 10.3448 |
|
77 |
+
| 0.0002 | 10.0 | 210 | 0.0195 | 10.3448 |
|
78 |
+
|
79 |
+
|
80 |
+
### Framework versions
|
81 |
+
|
82 |
+
- Transformers 4.40.2
|
83 |
+
- Pytorch 2.2.1+cu121
|
84 |
+
- Datasets 2.19.1
|
85 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "tarteel-ai/whisper-base-ar-quran",
|
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": 512,
|
17 |
+
"decoder_attention_heads": 8,
|
18 |
+
"decoder_ffn_dim": 2048,
|
19 |
+
"decoder_layerdrop": 0.0,
|
20 |
+
"decoder_layers": 6,
|
21 |
+
"decoder_start_token_id": 50258,
|
22 |
+
"dropout": 0.0,
|
23 |
+
"encoder_attention_heads": 8,
|
24 |
+
"encoder_ffn_dim": 2048,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 6,
|
27 |
+
"eos_token_id": 50257,
|
28 |
+
"forced_decoder_ids": [
|
29 |
+
[
|
30 |
+
1,
|
31 |
+
50272
|
32 |
+
],
|
33 |
+
[
|
34 |
+
2,
|
35 |
+
50359
|
36 |
+
],
|
37 |
+
[
|
38 |
+
3,
|
39 |
+
50363
|
40 |
+
]
|
41 |
+
],
|
42 |
+
"init_std": 0.02,
|
43 |
+
"is_encoder_decoder": true,
|
44 |
+
"mask_feature_length": 10,
|
45 |
+
"mask_feature_min_masks": 0,
|
46 |
+
"mask_feature_prob": 0.0,
|
47 |
+
"mask_time_length": 10,
|
48 |
+
"mask_time_min_masks": 2,
|
49 |
+
"mask_time_prob": 0.05,
|
50 |
+
"max_length": 1024,
|
51 |
+
"max_source_positions": 1500,
|
52 |
+
"max_target_positions": 448,
|
53 |
+
"median_filter_width": 7,
|
54 |
+
"model_type": "whisper",
|
55 |
+
"num_hidden_layers": 6,
|
56 |
+
"num_mel_bins": 80,
|
57 |
+
"pad_token_id": 50257,
|
58 |
+
"scale_embedding": false,
|
59 |
+
"suppress_tokens": [],
|
60 |
+
"torch_dtype": "float32",
|
61 |
+
"transformers_version": "4.40.2",
|
62 |
+
"use_cache": false,
|
63 |
+
"use_weighted_layer_sum": false,
|
64 |
+
"vocab_size": 51865
|
65 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"begin_suppress_tokens": [
|
3 |
+
220,
|
4 |
+
50257
|
5 |
+
],
|
6 |
+
"bos_token_id": 50257,
|
7 |
+
"decoder_start_token_id": 50258,
|
8 |
+
"eos_token_id": 50257,
|
9 |
+
"forced_decoder_ids": [
|
10 |
+
[
|
11 |
+
1,
|
12 |
+
50272
|
13 |
+
],
|
14 |
+
[
|
15 |
+
2,
|
16 |
+
50359
|
17 |
+
],
|
18 |
+
[
|
19 |
+
3,
|
20 |
+
50363
|
21 |
+
]
|
22 |
+
],
|
23 |
+
"max_length": 1024,
|
24 |
+
"pad_token_id": 50257,
|
25 |
+
"suppress_tokens": [],
|
26 |
+
"transformers_version": "4.40.2",
|
27 |
+
"use_cache": false
|
28 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:543e65249aaf69cad9b483601aad8054c9745bf9c641bb048d768262a6315cd5
|
3 |
+
size 290403936
|
preprocessor_config.json
ADDED
@@ -0,0 +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 |
+
}
|
runs/May09_17-56-05_70784b0afc4f/events.out.tfevents.1715277375.70784b0afc4f.181.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5980ed7046c96328ded4939a99b810fa03a80a0c8b134a231dbdd3289598fba
|
3 |
+
size 11190
|
runs/May09_18-26-37_70784b0afc4f/events.out.tfevents.1715279208.70784b0afc4f.181.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5611e373b43ac1adaf09bdd0b8c9d061ab70ea0efb2ffa949fb4aa70705af722
|
3 |
+
size 11189
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e94aefd413b36fb79dca0053e1d1238e6a0465cbe829b18d4619073b0865662
|
3 |
+
size 5112
|