End of training

README.md

@@ -2,6 +2,7 @@
 language:
 - tr
 license: apache-2.0
+base_model: openai/whisper-small
 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
+- name: Whisper Small 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
@@ -23,20 +23,20 @@ model-index:
       split: None
       args: 'config: tr, split: test'
     metrics:
-    - type: wer
-      value: 58.751043061458155
-      name: Wer
+    - name: Wer
+      type: wer
+      value: 43.06339873086104
 ---
 
 <!-- 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 Tiny Tr - Canberk Kandemir
+# Whisper Small Tr - Canberk Kandemir
 
-This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 11.0 dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5555
-- Wer: 58.7510
+- Loss: 0.5432
+- Wer: 43.0634
 
 ## Model description
 
@@ -55,13 +55,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 7e-05
 - train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
+- lr_scheduler_warmup_steps: 1000
 - training_steps: 5000
 - mixed_precision_training: Native AMP
 
@@ -69,8 +71,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.431         | 0.44  | 1000 | 0.6055          | 58.5124 |
-| 0.3695        | 0.89  | 2000 | 0.5555          | 58.7510 |
+| 0.4399        | 0.44  | 500  | 0.6307          | 61.0351 |
+| 0.4322        | 0.89  | 1000 | 0.6820          | 58.6909 |
+| 0.2857        | 1.33  | 1500 | 0.6496          | 54.3867 |
+| 0.2839        | 1.77  | 2000 | 0.6088          | 49.6497 |
+| 0.1467        | 2.21  | 2500 | 0.5813          | 47.3346 |
+| 0.1268        | 2.66  | 3000 | 0.5647          | 46.1315 |
+| 0.0711        | 3.1   | 3500 | 0.5532          | 44.8196 |
+| 0.0658        | 3.54  | 4000 | 0.5444          | 43.4670 |
+| 0.0601        | 3.99  | 4500 | 0.5372          | 43.4146 |
+| 0.0304        | 4.43  | 5000 | 0.5432          | 43.0634 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02985f2c19b1b2a60d757db97a93b643cfd86fe7d3cd29da8ea3d3a1cc2d661
+oid sha256:221f5022f120adee071bfb66fdfa145cf032bac1dc999e3282c927d55058a9ae
 size 151061672

runs/Feb18_23-24-20_d5cefe444400/events.out.tfevents.1708298674.d5cefe444400.2635.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:969f9808b63d069a73486ec8d9f78aa2107177b26c36cd514dce422889decce7
-size 36285
+oid sha256:ee5ee34ac960196204fb843e2a054012bbefeb5ee622cf7f211ee9fbbc7cea9a
+size 40097