Model save

README.md

@@ -5,7 +5,7 @@ base_model: openai/whisper-small
 tags:
 - generated_from_trainer
 datasets:
-- mozilla-foundation/common_voice_17_0
+- common_voice_17_0
 metrics:
 - wer
 model-index:
@@ -15,15 +15,15 @@ model-index:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: mozilla-foundation/common_voice_17_0 ar
-      type: mozilla-foundation/common_voice_17_0
+      name: common_voice_17_0
+      type: common_voice_17_0
       config: ar
       split: None
       args: ar
     metrics:
     - name: Wer
       type: wer
-      value: 0.7520215633423181
+      value: 0.3367421033522934
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-small-dar
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the mozilla-foundation/common_voice_17_0 ar dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_voice_17_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3785
-- Wer: 0.7520
+- Loss: 0.1813
+- Wer: 0.3367
 
 ## Model description
 
@@ -63,19 +63,19 @@ The following hyperparameters were used during training:
 - total_eval_batch_size: 32
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 50
-- training_steps: 500
+- lr_scheduler_warmup_steps: 100
+- training_steps: 1000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer    |
-|:-------------:|:-----:|:----:|:---------------:|:------:|
-| No log        | 20.0  | 100  | 1.2186          | 0.7466 |
-| No log        | 40.0  | 200  | 1.3032          | 0.7358 |
-| 0.0984        | 60.0  | 300  | 1.3486          | 0.7466 |
-| 0.0984        | 80.0  | 400  | 1.3713          | 0.7520 |
-| 0.0003        | 100.0 | 500  | 1.3785          | 0.7520 |
+| Training Loss | Epoch  | Step | Validation Loss | Wer    |
+|:-------------:|:------:|:----:|:---------------:|:------:|
+| 0.303         | 0.5935 | 200  | 0.2434          | 0.4226 |
+| 0.2           | 1.1869 | 400  | 0.2035          | 0.3914 |
+| 0.1633        | 1.7804 | 600  | 0.1876          | 0.3469 |
+| 0.106         | 2.3739 | 800  | 0.1850          | 0.3488 |
+| 0.1005        | 2.9674 | 1000 | 0.1813          | 0.3367 |
 
 
 ### Framework versions