update model card README.md

README.md

@@ -1,11 +1,13 @@
 ---
-license: apache-2.0
+language:
+- sv-SE
+license: cc0-1.0
 tags:
 - automatic-speech-recognition
-- NbAiLab/NPSC
+- mozilla-foundation/common_voice_7_0
 - generated_from_trainer
 datasets:
-- npsc
+- common_voice
 model-index:
 - name: xls-npsc-oh
   results: []
@@ -16,10 +18,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # xls-npsc-oh
 
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the NBAILAB/NPSC - 48K_MP3 dataset.
+This model is a fine-tuned version of [KBLab/wav2vec2-large-voxrex](https://huggingface.co/KBLab/wav2vec2-large-voxrex) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - SV-SE dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.0429
-- Wer: 1.0
+- Loss: 0.2314
+- Wer: 0.64
 
 ## Model description
 
@@ -38,16 +40,16 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 7.5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 32
+- total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 10.0
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 5.0
 - mixed_precision_training: Native AMP
 
 ### Training results