Model save

README.md

@@ -3,7 +3,6 @@ library_name: transformers
 license: apache-2.0
 base_model: openai/whisper-tiny
 tags:
-- audio-classification
 - generated_from_trainer
 metrics:
 - accuracy
@@ -17,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper_tiny_fleurs
 
-This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the /home/investigacion/disco4TB/workspace_pablo/firvox_whisper_research/finetunnig/dataset/dataset_parquet/dataset_1000x6_noFirVox_correctedpaths.parquet dataset.
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9658
-- Accuracy: 0.7744
+- Loss: 0.4373
+- Accuracy: 0.87
 
 ## Model description
 
@@ -51,14 +50,16 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 1.0
+- num_epochs: 3.0
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.0287        | 1.0   | 80   | 0.9658          | 0.7744   |
+| 0.9061        | 1.0   | 80   | 0.7686          | 0.7856   |
+| 0.4682        | 2.0   | 160  | 0.5186          | 0.8389   |
+| 0.286         | 3.0   | 240  | 0.4373          | 0.87     |
 
 
 ### Framework versions