End of training
Browse files
README.md
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
language:
|
| 3 |
- ar
|
| 4 |
license: apache-2.0
|
|
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
base_model: tarteel-ai/whisper-base-ar-quran
|
| 8 |
datasets:
|
| 9 |
- zolfa
|
| 10 |
metrics:
|
|
@@ -13,16 +13,16 @@ model-index:
|
|
| 13 |
- name: Whisper-raghadomar
|
| 14 |
results:
|
| 15 |
- task:
|
| 16 |
-
type: automatic-speech-recognition
|
| 17 |
name: Automatic Speech Recognition
|
|
|
|
| 18 |
dataset:
|
| 19 |
name: Zolfa Dataset
|
| 20 |
type: zolfa
|
| 21 |
args: 'config: ar, split: test'
|
| 22 |
metrics:
|
| 23 |
-
-
|
|
|
|
| 24 |
value: 6.896551724137931
|
| 25 |
-
name: Wer
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -32,7 +32,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 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.
|
| 36 |
- Wer: 6.8966
|
| 37 |
|
| 38 |
## Model description
|
|
@@ -53,7 +53,7 @@ More information needed
|
|
| 53 |
|
| 54 |
The following hyperparameters were used during training:
|
| 55 |
- learning_rate: 1e-05
|
| 56 |
-
- train_batch_size:
|
| 57 |
- eval_batch_size: 8
|
| 58 |
- seed: 42
|
| 59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
@@ -64,18 +64,18 @@ The following hyperparameters were used during training:
|
|
| 64 |
|
| 65 |
### Training results
|
| 66 |
|
| 67 |
-
| Training Loss | Epoch
|
| 68 |
-
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.0001 |
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
|
| 80 |
|
| 81 |
### Framework versions
|
|
|
|
| 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 |
- zolfa
|
| 10 |
metrics:
|
|
|
|
| 13 |
- name: Whisper-raghadomar
|
| 14 |
results:
|
| 15 |
- task:
|
|
|
|
| 16 |
name: Automatic Speech Recognition
|
| 17 |
+
type: automatic-speech-recognition
|
| 18 |
dataset:
|
| 19 |
name: Zolfa Dataset
|
| 20 |
type: zolfa
|
| 21 |
args: 'config: ar, split: test'
|
| 22 |
metrics:
|
| 23 |
+
- name: Wer
|
| 24 |
+
type: wer
|
| 25 |
value: 6.896551724137931
|
|
|
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 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: 0.0208
|
| 36 |
- Wer: 6.8966
|
| 37 |
|
| 38 |
## Model description
|
|
|
|
| 53 |
|
| 54 |
The following hyperparameters were used during training:
|
| 55 |
- learning_rate: 1e-05
|
| 56 |
+
- train_batch_size: 4
|
| 57 |
- eval_batch_size: 8
|
| 58 |
- seed: 42
|
| 59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
|
|
| 64 |
|
| 65 |
### Training results
|
| 66 |
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 68 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 69 |
+
| 0.0191 | 0.7143 | 100 | 0.0403 | 6.8966 |
|
| 70 |
+
| 0.0065 | 1.4286 | 200 | 0.0149 | 6.8966 |
|
| 71 |
+
| 0.009 | 2.1429 | 300 | 0.0263 | 6.8966 |
|
| 72 |
+
| 0.0106 | 2.8571 | 400 | 0.0417 | 6.8966 |
|
| 73 |
+
| 0.0011 | 3.5714 | 500 | 0.0195 | 6.8966 |
|
| 74 |
+
| 0.0028 | 4.2857 | 600 | 0.0223 | 6.8966 |
|
| 75 |
+
| 0.0001 | 5.0 | 700 | 0.0188 | 6.8966 |
|
| 76 |
+
| 0.0017 | 5.7143 | 800 | 0.0212 | 6.8966 |
|
| 77 |
+
| 0.0001 | 6.4286 | 900 | 0.0199 | 6.8966 |
|
| 78 |
+
| 0.0009 | 7.1429 | 1000 | 0.0208 | 6.8966 |
|
| 79 |
|
| 80 |
|
| 81 |
### Framework versions
|
generation_config.json
CHANGED
|
@@ -1,4 +1,46 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"begin_suppress_tokens": [
|
| 3 |
220,
|
| 4 |
50257
|
|
@@ -20,9 +62,118 @@
|
|
| 20 |
50363
|
| 21 |
]
|
| 22 |
],
|
| 23 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 24 |
"pad_token_id": 50257,
|
|
|
|
|
|
|
| 25 |
"suppress_tokens": [],
|
| 26 |
-
"
|
| 27 |
-
|
|
|
|
|
|
|
|
|
|
| 28 |
}
|
|
|
|
| 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": [
|
| 45 |
220,
|
| 46 |
50257
|
|
|
|
| 62 |
50363
|
| 63 |
]
|
| 64 |
],
|
| 65 |
+
"is_multilingual": true,
|
| 66 |
+
"lang_to_id": {
|
| 67 |
+
"<|af|>": 50327,
|
| 68 |
+
"<|am|>": 50334,
|
| 69 |
+
"<|ar|>": 50272,
|
| 70 |
+
"<|as|>": 50350,
|
| 71 |
+
"<|az|>": 50304,
|
| 72 |
+
"<|ba|>": 50355,
|
| 73 |
+
"<|be|>": 50330,
|
| 74 |
+
"<|bg|>": 50292,
|
| 75 |
+
"<|bn|>": 50302,
|
| 76 |
+
"<|bo|>": 50347,
|
| 77 |
+
"<|br|>": 50309,
|
| 78 |
+
"<|bs|>": 50315,
|
| 79 |
+
"<|ca|>": 50270,
|
| 80 |
+
"<|cs|>": 50283,
|
| 81 |
+
"<|cy|>": 50297,
|
| 82 |
+
"<|da|>": 50285,
|
| 83 |
+
"<|de|>": 50261,
|
| 84 |
+
"<|el|>": 50281,
|
| 85 |
+
"<|en|>": 50259,
|
| 86 |
+
"<|es|>": 50262,
|
| 87 |
+
"<|et|>": 50307,
|
| 88 |
+
"<|eu|>": 50310,
|
| 89 |
+
"<|fa|>": 50300,
|
| 90 |
+
"<|fi|>": 50277,
|
| 91 |
+
"<|fo|>": 50338,
|
| 92 |
+
"<|fr|>": 50265,
|
| 93 |
+
"<|gl|>": 50319,
|
| 94 |
+
"<|gu|>": 50333,
|
| 95 |
+
"<|haw|>": 50352,
|
| 96 |
+
"<|ha|>": 50354,
|
| 97 |
+
"<|he|>": 50279,
|
| 98 |
+
"<|hi|>": 50276,
|
| 99 |
+
"<|hr|>": 50291,
|
| 100 |
+
"<|ht|>": 50339,
|
| 101 |
+
"<|hu|>": 50286,
|
| 102 |
+
"<|hy|>": 50312,
|
| 103 |
+
"<|id|>": 50275,
|
| 104 |
+
"<|is|>": 50311,
|
| 105 |
+
"<|it|>": 50274,
|
| 106 |
+
"<|ja|>": 50266,
|
| 107 |
+
"<|jw|>": 50356,
|
| 108 |
+
"<|ka|>": 50329,
|
| 109 |
+
"<|kk|>": 50316,
|
| 110 |
+
"<|km|>": 50323,
|
| 111 |
+
"<|kn|>": 50306,
|
| 112 |
+
"<|ko|>": 50264,
|
| 113 |
+
"<|la|>": 50294,
|
| 114 |
+
"<|lb|>": 50345,
|
| 115 |
+
"<|ln|>": 50353,
|
| 116 |
+
"<|lo|>": 50336,
|
| 117 |
+
"<|lt|>": 50293,
|
| 118 |
+
"<|lv|>": 50301,
|
| 119 |
+
"<|mg|>": 50349,
|
| 120 |
+
"<|mi|>": 50295,
|
| 121 |
+
"<|mk|>": 50308,
|
| 122 |
+
"<|ml|>": 50296,
|
| 123 |
+
"<|mn|>": 50314,
|
| 124 |
+
"<|mr|>": 50320,
|
| 125 |
+
"<|ms|>": 50282,
|
| 126 |
+
"<|mt|>": 50343,
|
| 127 |
+
"<|my|>": 50346,
|
| 128 |
+
"<|ne|>": 50313,
|
| 129 |
+
"<|nl|>": 50271,
|
| 130 |
+
"<|nn|>": 50342,
|
| 131 |
+
"<|no|>": 50288,
|
| 132 |
+
"<|oc|>": 50328,
|
| 133 |
+
"<|pa|>": 50321,
|
| 134 |
+
"<|pl|>": 50269,
|
| 135 |
+
"<|ps|>": 50340,
|
| 136 |
+
"<|pt|>": 50267,
|
| 137 |
+
"<|ro|>": 50284,
|
| 138 |
+
"<|ru|>": 50263,
|
| 139 |
+
"<|sa|>": 50344,
|
| 140 |
+
"<|sd|>": 50332,
|
| 141 |
+
"<|si|>": 50322,
|
| 142 |
+
"<|sk|>": 50298,
|
| 143 |
+
"<|sl|>": 50305,
|
| 144 |
+
"<|sn|>": 50324,
|
| 145 |
+
"<|so|>": 50326,
|
| 146 |
+
"<|sq|>": 50317,
|
| 147 |
+
"<|sr|>": 50303,
|
| 148 |
+
"<|su|>": 50357,
|
| 149 |
+
"<|sv|>": 50273,
|
| 150 |
+
"<|sw|>": 50318,
|
| 151 |
+
"<|ta|>": 50287,
|
| 152 |
+
"<|te|>": 50299,
|
| 153 |
+
"<|tg|>": 50331,
|
| 154 |
+
"<|th|>": 50289,
|
| 155 |
+
"<|tk|>": 50341,
|
| 156 |
+
"<|tl|>": 50348,
|
| 157 |
+
"<|tr|>": 50268,
|
| 158 |
+
"<|tt|>": 50351,
|
| 159 |
+
"<|uk|>": 50280,
|
| 160 |
+
"<|ur|>": 50290,
|
| 161 |
+
"<|uz|>": 50337,
|
| 162 |
+
"<|vi|>": 50278,
|
| 163 |
+
"<|yi|>": 50335,
|
| 164 |
+
"<|yo|>": 50325,
|
| 165 |
+
"<|zh|>": 50260
|
| 166 |
+
},
|
| 167 |
+
"max_initial_timestamp_index": 50,
|
| 168 |
+
"max_length": 448,
|
| 169 |
+
"no_timestamps_token_id": 50363,
|
| 170 |
"pad_token_id": 50257,
|
| 171 |
+
"prev_sot_token_id": 50361,
|
| 172 |
+
"return_timestamps": false,
|
| 173 |
"suppress_tokens": [],
|
| 174 |
+
"task_to_id": {
|
| 175 |
+
"transcribe": 50359,
|
| 176 |
+
"translate": 50358
|
| 177 |
+
},
|
| 178 |
+
"transformers_version": "4.41.2"
|
| 179 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 966995080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac8e53cc7da935762bfc32d280c1b64f42449e601200742fd0ca1e8fdb81ed19
|
| 3 |
size 966995080
|
runs/Jun04_13-58-48_f74e2541c0b0/events.out.tfevents.1717509540.f74e2541c0b0.195.2
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 sha256:6be56857a266e18beb6d3e81bfafeafd64355e1d03e0c84295e82b3f0be29d6d
|
| 3 |
+
size 19803
|