End of training

README.md

@@ -7,36 +7,36 @@ base_model: openai/whisper-small
 tags:
 - generated_from_trainer
 datasets:
-- mozilla-foundation/common_voice_16_1
+- mozilla-foundation/common_voice_17_0
 metrics:
 - wer
 model-index:
-- name: Whisper Small Canontese X v1
+- name: Whisper Small Canontese X v2
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: Common Voice 11.0
-      type: mozilla-foundation/common_voice_16_1
-      config: zh-HK
+      name: Common Voice 16.1 and 17.0
+      type: mozilla-foundation/common_voice_17_0
+      config: yue
       split: None
       args: 'config: zh-HK, split: test'
     metrics:
     - name: Wer
       type: wer
-      value: 63.091001525165225
+      value: 54.825384904243336
 ---
 
 <!-- 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 Canontese X v1
+# Whisper Small Canontese X v2
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.1 and 17.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2768
-- Wer: 63.0910
+- Loss: 0.2264
+- Wer: 54.8254
 
 ## Model description
 
@@ -69,9 +69,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Wer     |
 |:-------------:|:------:|:----:|:---------------:|:-------:|
-| 0.4043        | 0.4598 | 1000 | 0.3661          | 72.7250 |
-| 0.3677        | 0.9195 | 2000 | 0.2965          | 65.8617 |
-| 0.1541        | 1.3793 | 3000 | 0.2768          | 63.0910 |
+| 0.2578        | 0.6954 | 1000 | 0.2680          | 61.4345 |
+| 0.0892        | 1.3908 | 2000 | 0.2376          | 57.3789 |
+| 0.0295        | 2.0862 | 3000 | 0.2264          | 54.8254 |
 
 
 ### Framework versions