End of training

README.md

@@ -1,35 +1,80 @@
 ---
-base_model: openai/whisper-small
-datasets:
-- mozilla-foundation/common_voice_17_0
-language: el
 library_name: transformers
 license: apache-2.0
+base_model: openai/whisper-small
+tags:
+- generated_from_trainer
+datasets:
+- common_voice_17_0
+metrics:
+- wer
 model-index:
-- name: Finetuned openai/whisper-small on Greek
+- name: whisper-small-el
   results:
   - task:
+      name: Automatic Speech Recognition
       type: automatic-speech-recognition
-      name: Speech-to-Text
     dataset:
-      name: Common Voice (Greek)
-      type: common_voice
+      name: common_voice_17_0
+      type: common_voice_17_0
+      config: el
+      split: None
+      args: el
     metrics:
-    - type: wer
-      value: 30.644
+    - name: Wer
+      type: wer
+      value: 45.63223714682724
 ---
 
-# Finetuned openai/whisper-small on 3620 Greek training audio samples from mozilla-foundation/common_voice_17_0.
+<!-- 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. -->
+
+# whisper-small-el
+
+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: 0.8687
+- Model Preparation Time: 0.0059
+- Wer: 45.6322
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- 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: 14
+- mixed_precision_training: Native AMP
+
+### Training results
 
-This model was created from the Mozilla.ai Blueprint:
-[speech-to-text-finetune](https://github.com/mozilla-ai/speech-to-text-finetune).
+| Training Loss | Epoch  | Step | Validation Loss | Model Preparation Time | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:----------------------:|:-------:|
+| 0.8509        | 0.0439 | 5    | 0.9019          | 0.0059                 | 46.4382 |
+| 0.8082        | 0.0877 | 10   | 0.8687          | 0.0059                 | 45.6322 |
 
-## Evaluation results on 1701 audio samples of Greek:
 
-### Baseline model (before finetuning) on Greek
-- Word Error Rate: 46.401
-- Loss: 0.902
+### Framework versions
 
-### Finetuned model (after finetuning) on Greek
-- Word Error Rate: 30.644
-- Loss: 0.387
+- Transformers 4.48.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.3.1
+- Tokenizers 0.21.0

generation_config.json

@@ -250,5 +250,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.48.0"
+  "transformers_version": "4.48.3"
 }

runs/Feb18_15-35-04_52522ad1ab90/events.out.tfevents.1739893609.52522ad1ab90.3137.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3da2e1d6e2bb45ad184fda99d9bbfb84cf1dd210a955de4f31eb325b4277df25
-size 8339
+oid sha256:eec942918fc9ef8e2969fcb689088c21d029529edee660e7a46d1e23218b1676
+size 8687

runs/Feb18_15-35-04_52522ad1ab90/events.out.tfevents.1739896002.52522ad1ab90.3137.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d0e220299c86321faf4bf443c7a01c59bbdc8ff029be1d1e41f2937119ff8e
+size 465