Model save
Browse files
README.md
CHANGED
|
@@ -1,27 +1,25 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
-
language:
|
| 4 |
-
- ar
|
| 5 |
license: apache-2.0
|
| 6 |
-
base_model:
|
| 7 |
tags:
|
| 8 |
- generated_from_trainer
|
| 9 |
metrics:
|
| 10 |
- wer
|
| 11 |
model-index:
|
| 12 |
-
- name:
|
| 13 |
results: []
|
| 14 |
---
|
| 15 |
|
| 16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
|
| 19 |
-
#
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
-
- Wer: 0.
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
@@ -49,23 +47,48 @@ The following hyperparameters were used during training:
|
|
| 49 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 50 |
- lr_scheduler_type: linear
|
| 51 |
- lr_scheduler_warmup_steps: 500
|
| 52 |
-
- num_epochs:
|
| 53 |
- mixed_precision_training: Native AMP
|
| 54 |
|
| 55 |
### Training results
|
| 56 |
|
| 57 |
-
| Training Loss | Epoch | Step
|
| 58 |
-
|
| 59 |
-
| 46.3716 | 0.2851 | 400
|
| 60 |
-
| 16.3386 | 0.5701 | 800
|
| 61 |
-
| 11.9313 | 0.8552 | 1200
|
| 62 |
-
| 8.1383 | 1.1397 | 1600
|
| 63 |
-
| 6.2069 | 1.4247 | 2000
|
| 64 |
-
| 5.6497 | 1.7098 | 2400
|
| 65 |
-
| 5.2035 | 1.9948 | 2800
|
| 66 |
-
| 4.7207 | 2.2794 | 3200
|
| 67 |
-
| 4.1488 | 2.5644 | 3600
|
| 68 |
-
| 4.0903 | 2.8495 | 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
|
| 70 |
|
| 71 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
|
|
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
+
base_model: Baselhany/Distilation_Whisper_base_CKP
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- wer
|
| 9 |
model-index:
|
| 10 |
+
- name: Distilation_Whisper_base_CKP
|
| 11 |
results: []
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
|
| 17 |
+
# Distilation_Whisper_base_CKP
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Baselhany/Distilation_Whisper_base_CKP](https://huggingface.co/Baselhany/Distilation_Whisper_base_CKP) on an unknown dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.1073
|
| 22 |
+
- Wer: 0.2214
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 47 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
- lr_scheduler_warmup_steps: 500
|
| 50 |
+
- num_epochs: 10
|
| 51 |
- mixed_precision_training: Native AMP
|
| 52 |
|
| 53 |
### Training results
|
| 54 |
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 56 |
+
|:-------------:|:------:|:-----:|:---------------:|:------:|
|
| 57 |
+
| 46.3716 | 0.2851 | 400 | 0.1697 | 0.6098 |
|
| 58 |
+
| 16.3386 | 0.5701 | 800 | 0.1358 | 0.3553 |
|
| 59 |
+
| 11.9313 | 0.8552 | 1200 | 0.1236 | 0.3021 |
|
| 60 |
+
| 8.1383 | 1.1397 | 1600 | 0.1211 | 0.2676 |
|
| 61 |
+
| 6.2069 | 1.4247 | 2000 | 0.1188 | 0.2626 |
|
| 62 |
+
| 5.6497 | 1.7098 | 2400 | 0.1146 | 0.2371 |
|
| 63 |
+
| 5.2035 | 1.9948 | 2800 | 0.1113 | 0.2395 |
|
| 64 |
+
| 4.7207 | 2.2794 | 3200 | 0.1112 | 0.2258 |
|
| 65 |
+
| 4.1488 | 2.5644 | 3600 | 0.1108 | 0.2389 |
|
| 66 |
+
| 4.0903 | 2.8495 | 4000 | 0.1094 | 0.2219 |
|
| 67 |
+
| 4.2814 | 3.1361 | 4400 | 0.1135 | 0.2302 |
|
| 68 |
+
| 4.0634 | 3.4212 | 4800 | 0.1100 | 0.2300 |
|
| 69 |
+
| 3.8832 | 3.7062 | 5200 | 0.1101 | 0.2203 |
|
| 70 |
+
| 4.0159 | 3.9913 | 5600 | 0.1073 | 0.2238 |
|
| 71 |
+
| 3.1347 | 4.2758 | 6000 | 0.1089 | 0.2230 |
|
| 72 |
+
| 3.4745 | 4.5608 | 6400 | 0.1049 | 0.2140 |
|
| 73 |
+
| 3.1785 | 4.8459 | 6800 | 0.1070 | 0.2119 |
|
| 74 |
+
| 2.8142 | 5.1304 | 7200 | 0.1034 | 0.2094 |
|
| 75 |
+
| 2.6992 | 5.4155 | 7600 | 0.1051 | 0.2149 |
|
| 76 |
+
| 2.5099 | 5.7005 | 8000 | 0.1071 | 0.2203 |
|
| 77 |
+
| 2.4995 | 5.9856 | 8400 | 0.1032 | 0.2216 |
|
| 78 |
+
| 2.1725 | 6.2701 | 8800 | 0.1032 | 0.2318 |
|
| 79 |
+
| 2.171 | 6.5551 | 9200 | 0.1023 | 0.2187 |
|
| 80 |
+
| 2.3072 | 6.8402 | 9600 | 0.1019 | 0.2191 |
|
| 81 |
+
| 1.9543 | 7.1247 | 10000 | 0.1028 | 0.2119 |
|
| 82 |
+
| 2.0848 | 7.4098 | 10400 | 0.1017 | 0.2112 |
|
| 83 |
+
| 1.9636 | 7.6948 | 10800 | 0.1020 | 0.2159 |
|
| 84 |
+
| 1.9283 | 7.9799 | 11200 | 0.1010 | 0.2131 |
|
| 85 |
+
| 1.8101 | 8.2644 | 11600 | 0.1010 | 0.2107 |
|
| 86 |
+
| 1.9462 | 8.5494 | 12000 | 0.1010 | 0.2137 |
|
| 87 |
+
| 1.9585 | 8.8345 | 12400 | 0.1006 | 0.2151 |
|
| 88 |
+
| 1.6228 | 9.1190 | 12800 | 0.1005 | 0.2160 |
|
| 89 |
+
| 1.7241 | 9.4041 | 13200 | 0.0999 | 0.2218 |
|
| 90 |
+
| 1.7732 | 9.6891 | 13600 | 0.1001 | 0.2163 |
|
| 91 |
+
| 1.6427 | 9.9742 | 14000 | 0.1001 | 0.2157 |
|
| 92 |
|
| 93 |
|
| 94 |
### Framework versions
|
generation_config.json
CHANGED
|
@@ -65,20 +65,7 @@
|
|
| 65 |
"1": "LABEL_1"
|
| 66 |
},
|
| 67 |
"init_std": 0.02,
|
| 68 |
-
"input_ids":
|
| 69 |
-
[
|
| 70 |
-
1,
|
| 71 |
-
50272
|
| 72 |
-
],
|
| 73 |
-
[
|
| 74 |
-
2,
|
| 75 |
-
50359
|
| 76 |
-
],
|
| 77 |
-
[
|
| 78 |
-
3,
|
| 79 |
-
50363
|
| 80 |
-
]
|
| 81 |
-
],
|
| 82 |
"is_decoder": false,
|
| 83 |
"is_encoder_decoder": true,
|
| 84 |
"is_multilingual": true,
|
|
|
|
| 65 |
"1": "LABEL_1"
|
| 66 |
},
|
| 67 |
"init_std": 0.02,
|
| 68 |
+
"input_ids": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
"is_decoder": false,
|
| 70 |
"is_encoder_decoder": true,
|
| 71 |
"is_multilingual": true,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 223144592
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6f1cb55752a813c3cb34eca50717ca9a3a3adf2f4c4a972bb85d6d85e1b2a28
|
| 3 |
size 223144592
|
runs/May23_01-47-39_e1661d92042b/events.out.tfevents.1748002945.e1661d92042b.19.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37454bffa40912f4f8afca8ae7dbe2a0f3ee35d1b0d8432e555f5f502ba2a265
|
| 3 |
+
size 406
|