Update README.md

README.md

@@ -130,6 +130,18 @@ The following hyperparameters were used during training:
 - Datasets 1.17.1.dev0
 - Tokenizers 0.10.3
 
+### To evaluate on mozilla-foundation/common_voice_7_0 - test
+
+```bash
+python eval.py --model_id hf-test/xls-r-300m-sv --dataset mozilla-foundation/common_voice_7_0 --config sv-SE --split test
+```
+
+### To evaluate on speech-recognition-community-v2/dev_data
+
+```bash
+python eval.py --model_id hf-test/xls-r-300m-sv --dataset speech-recognition-community-v2/dev_data --config sv --split validation --chunk_length_s 5.0 --stride_length_s 1.0
+```
+
 ### Inference With LM
 
 ```python
@@ -163,3 +175,5 @@ transcription = processor.batch_decode(logits.numpy()).text
 | Without LM | With LM (run `./eval.py`) |
 |---|---|
 | 27.30 | 18.85 |
+
+