End of training

README.md

@@ -1,7 +1,8 @@
 ---
 language:
 - gn
-base_model: openai/whisper-base-wer
+license: apache-2.0
+base_model: openai/whisper-base
 tags:
 - generated_from_trainer
 datasets:
@@ -23,7 +24,7 @@ model-index:
     metrics:
     - name: Wer
       type: wer
-      value: 58.76017233125898
+      value: 58.90378171373863
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +32,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Common Voice 16 - Guarani
 
-This model is a fine-tuned version of [openai/whisper-base-wer](https://huggingface.co/openai/whisper-base-wer) on the Common Voice 16 dataset.
+This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the Common Voice 16 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5941
-- Wer: 58.7602
+- Loss: 0.5927
+- Wer: 58.9038
 
 ## Model description
 
@@ -59,23 +60,24 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant_with_warmup
+- lr_scheduler_warmup_steps: 50
 - training_steps: 500
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Wer     |
-|:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 1.5842        | 1.01  | 100  | 0.8536          | 78.7937 |
-| 0.5303        | 2.02  | 200  | 0.6709          | 68.3102 |
-| 0.3101        | 3.03  | 300  | 0.6054          | 63.0445 |
-| 0.1882        | 4.04  | 400  | 0.5909          | 60.3159 |
-| 0.1156        | 5.05  | 500  | 0.5941          | 58.7602 |
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 2.3403        | 1.0101 | 100  | 0.9377          | 81.1872 |
+| 0.5917        | 2.0202 | 200  | 0.6872          | 69.3633 |
+| 0.3348        | 3.0303 | 300  | 0.6128          | 65.4380 |
+| 0.2026        | 4.0404 | 400  | 0.5885          | 61.0340 |
+| 0.1237        | 5.0505 | 500  | 0.5927          | 58.9038 |
 
 
 ### Framework versions
 
-- Transformers 4.38.2
+- Transformers 4.40.0
 - Pytorch 2.2.1+cu121
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- Datasets 2.19.0
+- Tokenizers 0.19.1

generation_config.json

@@ -252,5 +252,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.38.2"
+  "transformers_version": "4.40.0"
 }