Rijgersberg
/

whisper-small-fy-NL

Automatic Speech Recognition

Generated from Trainer

Inference Endpoints

Model card Files Files and versions Metrics Training metrics Community

Edwin Rijgersberg commited on Oct 26, 2022

Commit

abf3c9d

·

1 Parent(s): 9b49b78

Update README.md

Add dataset info and WER before finetuning.

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -12,11 +12,13 @@ should probably proofread and complete it, then remove this comment. -->
 # whisper-small-fy-NL
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.5276
 - Wer: 0.2919
 ## Model description
 More information needed

 # whisper-small-fy-NL
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the [CommonVoice 11 `fy-NL` (West-Frisian)](https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0/viewer/fy-NL/train) dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.5276
 - Wer: 0.2919
+The Wer before finetuning was 1.0622.
 ## Model description
 More information needed