End of training

README.md

@@ -10,7 +10,7 @@ datasets:
 metrics:
 - wer
 model-index:
-- name: "Whisper Small Espa\xF1ol"
+- name: "Whisper Small Espa\xF1ol 2.0"
   results:
   - task:
       name: Automatic Speech Recognition
@@ -19,23 +19,23 @@ model-index:
       name: Common Voice 11.0
       type: mozilla-foundation/common_voice_11_0
       config: es
-      split: None
+      split: test
       args: 'config: es, split: test'
     metrics:
     - name: Wer
       type: wer
-      value: 20.74384494499738
+      value: 16.209450830140483
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# Whisper Small Español
+# Whisper Small Español 2.0
 
 This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5638
-- Wer: 20.7438
+- Loss: 0.3763
+- Wer: 16.2095
 
 ## Model description
 
@@ -66,12 +66,12 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Wer     |
-|:-------------:|:-------:|:----:|:---------------:|:-------:|
-| 0.0012        | 15.8730 | 1000 | 0.5054          | 20.3772 |
-| 0.0003        | 31.7460 | 2000 | 0.5381          | 20.5343 |
-| 0.0002        | 47.6190 | 3000 | 0.5559          | 20.7962 |
-| 0.0001        | 63.4921 | 4000 | 0.5638          | 20.7438 |
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.1289        | 1.6   | 1000 | 0.3013          | 18.0128 |
+| 0.0243        | 3.2   | 2000 | 0.3383          | 16.2401 |
+| 0.0079        | 4.8   | 3000 | 0.3608          | 16.2146 |
+| 0.0027        | 6.4   | 4000 | 0.3763          | 16.2095 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19800e8d6e316b49e2fc5ceda14e427981e8e9d3f4834ff3e2e83a478c3ccf84
+oid sha256:53ebbde0491c28b5e63eb4c0200134589d42faa5d5a1b91bc73e35ad0c28a5e4
 size 966995080

runs/Jul08_00-49-35_daa40fb9b81e/events.out.tfevents.1720399778.daa40fb9b81e.148.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54498dbf9db23d020373394c0fa32def78fc79545ff77343ac0d8106ac220f22
+size 41976

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1cb4558382836b2c64ba11cbb113981ef5dcc1a74c5a65693766c707d504a03
+oid sha256:98b20d70dd5ece88cbeea951e943a2c8656e9065f70ddbb2660aa80600b6c219
 size 5240