update model card README.md

README.md

@@ -1,6 +1,6 @@
 ---
 language:
-- hi
+- zh-CN
 license: apache-2.0
 tags:
 - hf-asr-leaderboard
@@ -10,7 +10,7 @@ datasets:
 metrics:
 - wer
 model-index:
-- name: Whisper Small Hi - Sanchit Gandhi
+- name: Whisper Small cn - howl
   results:
   - task:
       name: Automatic Speech Recognition
@@ -18,24 +18,24 @@ model-index:
     dataset:
       name: Common Voice 11.0
       type: mozilla-foundation/common_voice_11_0
-      config: hi
+      config: zh-CN
       split: test
-      args: 'config: hi, split: test'
+      args: 'config: zh-CN, split: test'
     metrics:
     - name: Wer
       type: wer
-      value: 31.61347667823584
+      value: 75.2976752976753
 ---
 
 <!-- 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 Hi - Sanchit Gandhi
+# Whisper Small cn - howl
 
 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: 0.4272
-- Wer: 31.6135
+- Loss: 0.3644
+- Wer: 75.2977
 
 ## Model description
 
@@ -61,17 +61,15 @@ 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: 4000
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Wer     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.0879        | 2.44  | 1000 | 0.2916          | 33.7213 |
-| 0.0212        | 4.89  | 2000 | 0.3454          | 32.9679 |
-| 0.0016        | 7.33  | 3000 | 0.4065          | 31.7447 |
-| 0.0005        | 9.78  | 4000 | 0.4272          | 31.6135 |
+| 0.2309        | 1.51  | 1000 | 0.3694          | 76.4411 |
+| 0.1069        | 3.02  | 2000 | 0.3644          | 75.2977 |
 
 
 ### Framework versions