End of training

README.md

@@ -9,9 +9,22 @@ tags:
 - generated_from_trainer
 datasets:
 - chinese_english
+metrics:
+- wer
 model-index:
 - name: Whisper tiny Chinese
-  results: []
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Chinese English
+      type: chinese_english
+      args: 'config: default, split: test'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 13.963463065925339
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -21,13 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Chinese English dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.9038
-- eval_wer: 26.1795
-- eval_runtime: 175.3742
-- eval_samples_per_second: 3.587
-- eval_steps_per_second: 3.587
-- epoch: 2.5674
-- step: 2000
+- Loss: 0.3321
+- Wer: 13.9635
 
 ## Model description
 
@@ -55,9 +63,18 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_steps: 500
 - num_epochs: 5
 
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.1227        | 1.2837 | 1000 | 0.3201          | 14.3606 |
+| 0.0461        | 2.5674 | 2000 | 0.3198          | 13.3916 |
+| 0.0128        | 3.8511 | 3000 | 0.3321          | 13.9635 |
+
+
 ### Framework versions
 
 - Transformers 4.48.3
 - Pytorch 2.6.0+cu124
-- Datasets 3.4.0
-- Tokenizers 0.21.0
+- Datasets 3.4.1
+- Tokenizers 0.21.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b57fd475722bf1958753bfc626a47abb1d191d4890fa844c9732a27aca95e85
+oid sha256:21f79455fe773162823658b8357e3f6edc189348a28a46ec39499207dd1db72a
 size 151061672