Update README.md

README.md

@@ -2,6 +2,7 @@
 license: apache-2.0
 tags:
 - generated_from_trainer
+- whisper-event
 metrics:
 - wer
 model-index:
@@ -14,10 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # whisper-medium-et-ERR2020
 
-This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.3672
-- Wer: 15.9119
+This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the following training sets: Common Voice 11, VoxPopuli, FLEURS and [ERR2020](http://bark.phon.ioc.ee/lw/korpused/ERR2020.html). The checkpoint-7000 was on [Whisper Event leaderboard](https://huggingface.co/spaces/whisper-event/winners?dataset=mozilla-foundation%2Fcommon_voice_11_0). Current score is for the final checkpoint. 
 
 ## Model description
 
@@ -61,10 +59,11 @@ The following hyperparameters were used during training:
 | 0.0459        | 1.13  | 9000  | 0.3704          | 17.9073 |
 | 0.0425        | 1.23  | 10000 | 0.3672          | 15.9119 |
 
+The validation set is combined from the validation sets of Common Voice 11, VoxPopuli, FLEURS and ERR2020.
 
 ### Framework versions
 
 - Transformers 4.26.0.dev0
-- Pytorch 1.12.1+rocm5.1.1
+- Pytorch 1.12.1+rocm5.1.1h
 - Datasets 2.7.1.dev0
 - Tokenizers 0.13.2