End of training

README.md

@@ -2,6 +2,7 @@
 language:
 - tr
 license: apache-2.0
+base_model: openai/whisper-tiny
 tags:
 - hf-asr-leaderboard
 - generated_from_trainer
@@ -9,13 +10,12 @@ datasets:
 - mozilla-foundation/common_voice_11_0
 metrics:
 - wer
-base_model: openai/whisper-tiny
 model-index:
 - name: Whisper Tiny Tr - Canberk Kandemir
   results:
   - task:
-      type: automatic-speech-recognition
       name: Automatic Speech Recognition
+      type: automatic-speech-recognition
     dataset:
       name: Common Voice 11.0
       type: mozilla-foundation/common_voice_11_0
@@ -23,9 +23,9 @@ model-index:
       split: None
       args: 'config: tr, split: test'
     metrics:
-    - type: wer
-      value: 46.32551279812152
-      name: Wer
+    - name: Wer
+      type: wer
+      value: 58.751043061458155
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,8 +35,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 11.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5251
-- Wer: 46.3255
+- Loss: 0.5555
+- Wer: 58.7510
 
 ## Model description
 
@@ -55,24 +55,22 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 32
-- eval_batch_size: 16
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 1000
-- training_steps: 2000
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 5000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.1699        | 0.44  | 500  | 0.5298          | 45.2446 |
-| 0.1401        | 0.89  | 1000 | 0.5348          | 47.2415 |
-| 0.1152        | 1.33  | 1500 | 0.5375          | 47.3560 |
-| 0.1602        | 1.77  | 2000 | 0.5251          | 46.3255 |
+| 0.431         | 0.44  | 1000 | 0.6055          | 58.5124 |
+| 0.3695        | 0.89  | 2000 | 0.5555          | 58.7510 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4748a6b6f059cc7d861a1bd72502023a22cb2db9b93ea7b5cb9d0126871c8402
+oid sha256:4c08e114714091a09000f33f881279ae35f917d768a665c4939a7725b4a91aeb
 size 151061672

runs/Feb18_15-33-30_6c823d512893/events.out.tfevents.1708270412.6c823d512893.1197.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f70a5b39ba1f44ced42a136225b9e3336338344a5805ec95e38b33712c703f
-size 18360
+oid sha256:64f8ada406ca83afdeb41450647bc5248d56b4e0f3f0d013340958664bce8681
+size 18714