End of training

README.md

@@ -2,12 +2,10 @@
 library_name: transformers
 language:
 - fr
-license: mit
-base_model: mlouala/whisper-diin-v2
+license: apache-2.0
+base_model: deepdml/whisper-large-v3-turbo
 tags:
 - generated_from_trainer
-datasets:
-- amphion/Emilia-Dataset
 model-index:
 - name: Whisper Diin - Part 3
   results: []
@@ -18,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Whisper Diin - Part 3
 
-This model is a fine-tuned version of [mlouala/whisper-diin-v2](https://huggingface.co/mlouala/whisper-diin-v2) on the Emilia-Dataset dataset.
+This model is a fine-tuned version of [deepdml/whisper-large-v3-turbo](https://huggingface.co/deepdml/whisper-large-v3-turbo) on the None dataset.
 
 ## Model description
 
@@ -44,7 +42,7 @@ The following hyperparameters were used during training:
 - 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: 500
-- training_steps: 5000
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -53,7 +51,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.48.0.dev0
+- Transformers 4.50.0.dev0
 - Pytorch 2.4.0
-- Datasets 3.2.0
+- Datasets 3.3.2
 - Tokenizers 0.21.0

generation_config.json

@@ -160,5 +160,5 @@
     "transcribe": 50360,
     "translate": 50359
   },
-  "transformers_version": "4.48.0.dev0"
+  "transformers_version": "4.50.0.dev0"
 }