End of training

README.md

@@ -8,17 +8,35 @@ tags:
 - generated_from_trainer
 datasets:
 - mozilla-foundation/common_voice_17_0
+metrics:
+- wer
 model-index:
-- name: openai/whisper-tiny - Greek
-  results: []
+- name: Baseline openai/whisper-tiny on Greek. Evaluated on 1701 audio samples
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: mozilla-foundation/common_voice_17_0- Greek
+      type: mozilla-foundation/common_voice_17_0
+      config: el
+      split: None
+      args: 'config: el, split: test'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 56.183418249189444
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# openai/whisper-tiny - Greek
+# Baseline openai/whisper-tiny on Greek. Evaluated on 1701 audio samples
 
-This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice dataset.
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the mozilla-foundation/common_voice_17_0- Greek dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8397
+- Wer: 56.1834
 
 ## Model description
 
@@ -44,16 +62,23 @@ The following hyperparameters were used during training:
 - optimizer: Use OptimizerNames.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
+- training_steps: 5000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
+| Training Loss | Epoch   | Step | Validation Loss | Wer     |
+|:-------------:|:-------:|:----:|:---------------:|:-------:|
+| 0.02          | 17.5439 | 1000 | 0.6888          | 56.2946 |
+| 0.0024        | 35.0877 | 2000 | 0.8397          | 56.1834 |
+| 0.001         | 52.6316 | 3000 | 0.9095          | 56.8041 |
+| 0.0006        | 70.1754 | 4000 | 0.9501          | 57.0079 |
+| 0.0005        | 87.7193 | 5000 | 0.9673          | 57.2487 |
 
 
 ### Framework versions
 
-- Transformers 4.47.1
+- Transformers 4.48.0
 - Pytorch 2.5.1+cu124
 - Datasets 3.2.0
 - Tokenizers 0.21.0

generation_config.json

@@ -236,5 +236,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.47.1"
+  "transformers_version": "4.48.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13c8f46b0c664e3b34ef54b5f0773938f4c0179eed2545d081c0e87fcf57b6f9
+oid sha256:e5e6e0dbda31c85ecd3936e1d265493a6239340373cfa31d3493d28e6af93e6e
 size 151061672

runs/Jan15_20-33-34_kostis/events.out.tfevents.1737004216.kostis.78030.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7c3710e3eb7ac8ec70f7cf906dd146406ac47eb51d036c0c190ea8784f33ddd
+size 406