End of training

README.md

@@ -4,26 +4,11 @@ license: apache-2.0
 base_model: openai/whisper-large-v3
 tags:
 - generated_from_trainer
-datasets:
-- audiofolder
 metrics:
 - wer
 model-index:
 - name: whisper-large-v3-chichewa
-  results:
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: audiofolder
-      type: audiofolder
-      config: default
-      split: None
-      args: default
-    metrics:
-    - name: Wer
-      type: wer
-      value: 61.98416006669446
+  results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,10 +16,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-large-v3-chichewa
 
-This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the audiofolder dataset.
+This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.8386
-- Wer: 61.9842
+- Loss: 3.1427
+- Wer: 101.3340
 
 ## Model description
 
@@ -65,18 +50,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch    | Step  | Validation Loss | Wer     |
-|:-------------:|:--------:|:-----:|:---------------:|:-------:|
-| 0.0224        | 15.3846  | 1000  | 1.4698          | 66.9862 |
-| 0.008         | 30.7692  | 2000  | 1.5184          | 63.7140 |
-| 0.0043        | 46.1538  | 3000  | 1.5825          | 68.4452 |
-| 0.0022        | 61.5385  | 4000  | 1.6392          | 62.1717 |
-| 0.0007        | 76.9231  | 5000  | 1.6587          | 63.8391 |
-| 0.0007        | 92.3077  | 6000  | 1.6862          | 63.6098 |
-| 0.0003        | 107.6923 | 7000  | 1.7792          | 62.7136 |
-| 0.0001        | 123.0769 | 8000  | 1.8105          | 62.2968 |
-| 0.0001        | 138.4615 | 9000  | 1.8290          | 62.1717 |
-| 0.0001        | 153.8462 | 10000 | 1.8386          | 61.9842 |
+| Training Loss | Epoch   | Step  | Validation Loss | Wer      |
+|:-------------:|:-------:|:-----:|:---------------:|:--------:|
+| 0.9229        | 7.0423  | 1000  | 2.0780          | 86.3539  |
+| 0.1427        | 14.0845 | 2000  | 2.5560          | 83.5493  |
+| 0.087         | 21.1268 | 3000  | 2.6909          | 80.8704  |
+| 0.0742        | 28.1690 | 4000  | 2.8007          | 81.8982  |
+| 0.065         | 35.2113 | 5000  | 2.8871          | 84.3639  |
+| 0.0627        | 42.2535 | 6000  | 2.9465          | 84.5334  |
+| 0.0586        | 49.2958 | 7000  | 3.0451          | 114.1600 |
+| 0.063         | 56.3380 | 8000  | 3.0983          | 82.6964  |
+| 0.0588        | 63.3803 | 9000  | 3.1352          | 81.0180  |
+| 0.0591        | 70.4225 | 10000 | 3.1427          | 101.3340 |
 
 
 ### Framework versions

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3110413debd96bcb34a8eb7f2e6cfb787334560a21ee3027bb9da67c18a391bb
+oid sha256:de507eb984156efd14f864021884894f6dbfc260d8266e38deb7cccbc453d85a
 size 4993448880

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e4acf75e280db1539dd4804bf492b258378aa6db679a0cc6319aa37cf885fc
+oid sha256:1eb4f5120f4b85bfb005216a0453e1896c28e53cbf75856e98b767336f283fe3
 size 1180663192