End of training

README.md

@@ -7,7 +7,7 @@ base_model: openai/whisper-small
 tags:
 - generated_from_trainer
 datasets:
-- mozilla-foundation/common_voice_11_0
+- mozilla-foundation/common_voice_16_0
 model-index:
 - name: Whisper Small Vi - Thai Hoa
   results: []
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Whisper Small Vi - Thai Hoa
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11 dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16 dataset.
 
 ## Model description
 
@@ -37,20 +37,18 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1.4004400000000001e-05
-- train_batch_size: 32
-- eval_batch_size: 16
+- learning_rate: 1e-05
+- train_batch_size: 64
+- eval_batch_size: 32
 - seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: constant_with_warmup
 - lr_scheduler_warmup_steps: 50
-- training_steps: 400
+- training_steps: 1400
 - mixed_precision_training: Native AMP
 
-### Training results
-
-
-
 ### Framework versions
 
 - Transformers 4.48.0.dev0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecf887dc79db8dcd84f83354e268ee061063ac98ab8ef0762056973ec8dc1fa4
+oid sha256:9d96beb5de53c773c7136b7c95d848d07a0e24c1504d5d038fbcb4a7178c9a11
 size 966995080

runs/Dec23_07-32-42_4ea5112da2c2/events.out.tfevents.1734939170.4ea5112da2c2.3166.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21bba1d77589465c0feb46d04c42712ea375965cff2ede386e4239c0fb25441a
+size 7413

runs/Dec23_07-47-42_4ea5112da2c2/events.out.tfevents.1734940069.4ea5112da2c2.8060.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a5d9ce1f3963b5d3f8547d286e98ff25cc47afe28d0b4b1d8f9cf78c9db55c2
+size 15813

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d5da925d4d1c1a80fb4b65d9d548f885f5c8839e21ebdd4b8184537695a8a8
+oid sha256:fff83268b72535cba11c0cb39aabd567a7116c40f3da640d28b79d93ef9db427
 size 5496