Model save

README.md

@@ -1,9 +1,9 @@
 ---
 library_name: peft
 license: apache-2.0
-base_model: openai/whisper-large-v3
+base_model: ivrit-ai/whisper-large-v3-turbo
 tags:
-- base_model:adapter:openai/whisper-large-v3
+- base_model:adapter:ivrit-ai/whisper-large-v3-turbo
 - lora
 - transformers
 metrics:
@@ -18,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-v4
 
-This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on an unknown dataset.
+This model is a fine-tuned version of [ivrit-ai/whisper-large-v3-turbo](https://huggingface.co/ivrit-ai/whisper-large-v3-turbo) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3231
-- Wer Ortho: 0.8194
-- Wer: 0.7037
+- Loss: 0.3019
+- Wer Ortho: 0.1547
+- Wer: 0.1048
 
 ## Model description
 
@@ -42,24 +42,24 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 1e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 16
-- total_train_batch_size: 64
+- total_train_batch_size: 128
 - 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: constant_with_warmup
+- lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 10
+- lr_scheduler_warmup_steps: 800
+- num_epochs: 5
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer Ortho | Wer    |
 |:-------------:|:------:|:----:|:---------------:|:---------:|:------:|
-| 1.3381        | 4.5664 | 100  | 1.3943          | 0.7563    | 0.6406 |
-| 1.2976        | 9.0944 | 200  | 1.3231          | 0.8194    | 0.7037 |
+| 0.3076        | 1.9608 | 100  | 0.3021          | 0.1497    | 0.0996 |
+| 0.308         | 3.9216 | 200  | 0.3019          | 0.1547    | 0.1048 |
 
 
 ### Framework versions