Model save

README.md

@@ -1,26 +1,24 @@
 ---
-language:
-- zh
 license: apache-2.0
-base_model: openai/whisper-small
+base_model: jun-han/whisper-small-zh
 tags:
 - generated_from_trainer
 datasets:
-- mozilla-foundation/common_voice_16_1
+- common_voice_16_1
 model-index:
-- name: Wisper-Small-zh
+- name: whisper-small
   results: []
 ---
 
 <!-- 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. -->
 
-# Wisper-Small-zh
+# whisper-small
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.1 dataset.
+This model is a fine-tuned version of [jun-han/whisper-small-zh](https://huggingface.co/jun-han/whisper-small-zh) on the common_voice_16_1 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6020
-- Cer: 33.3994
+- Loss: 0.3867
+- Cer: 21.2804
 
 ## Model description
 
@@ -46,15 +44,17 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
-- training_steps: 1000
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
-| Training Loss | Epoch  | Step | Validation Loss | Cer      |
-|:-------------:|:------:|:----:|:---------------:|:--------:|
-| 2.9388        | 0.6623 | 500  | 2.9818          | 102.7090 |
-| 0.5492        | 1.3245 | 1000 | 0.6020          | 33.3994  |
+| Training Loss | Epoch  | Step | Cer      | Validation Loss |
+|:-------------:|:------:|:----:|:--------:|:---------------:|
+| 2.9388        | 0.6623 | 500  | 102.7090 | 2.9818          |
+| 0.5492        | 1.3245 | 1000 | 33.3994  | 0.6020          |
+| 0.352         | 1.9868 | 1500 | 0.4214   | 23.2990         |
+| 0.2243        | 2.6490 | 2000 | 0.3867   | 21.2804         |
 
 
 ### Framework versions