update model card README.md

README.md

@@ -1,6 +1,10 @@
 ---
+language:
+- zh-TW
 license: apache-2.0
 tags:
+- automatic-speech-recognition
+- common_voice
 - generated_from_trainer
 datasets:
 - common_voice
@@ -14,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # 
 
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the COMMON_VOICE - ZH-TW dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1801
-- Wer: 0.8621
-- Cer: 0.2969
+- Loss: 1.1786
+- Wer: 0.8594
+- Cer: 0.2964
 
 ## Model description
 

nohup.out

@@ -15730,3 +15730,21 @@ Saving model checkpoint to ./
 Configuration saved in ./config.json
 Model weights saved in ./pytorch_model.bin
 Configuration saved in ./preprocessor_config.json
+***** eval metrics *****
+  epoch                   =      100.0
+  eval_cer                =     0.2964
+  eval_loss               =     1.1786
+  eval_runtime            = 0:02:06.01
+  eval_samples            =       2958
+  eval_samples_per_second =     23.473
+  eval_steps_per_second   =      2.936
+  eval_wer                =     0.8594
+
+   a214e6b..1db53a0  main -> main
+
+02/06/2022 21:57:09 - WARNING - huggingface_hub.repository - To https://huggingface.co/StevenLimcorn/wav2vec2-xls-r-300m-zh-TW
+   a214e6b..1db53a0  main -> main
+
+
+Dropping the following result as it does not have all the necessary fields:
+{'dataset': {'name': 'COMMON_VOICE - ZH-TW', 'type': 'common_voice', 'args': 'Config: zh-TW, Training split: train+validation, Eval split: test'}}