Upload folder using huggingface_hub

README.md

@@ -22,7 +22,7 @@ model-index:
       type: google/fleurs
     metrics:
     - type: wer
-      value: 78.3%
+      value: 77.3%
       name: test
 ---
 
@@ -33,7 +33,7 @@ This model was converted to MLX format from [`openai-whisper-tiny`](https://gith
 - `train` split of [openslr/openslr](https://huggingface.co/datasets/openslr/openslr) `SLR42`
 
 It achieves the following __word error rate__ (`wer`) on 2 popular datasets:
-- 78.3% on `test` split of [google/fleurs](https://huggingface.co/datasets/google/fleurs) `km-kh`
+- 77.3% on `test` split of [google/fleurs](https://huggingface.co/datasets/google/fleurs) `km-kh`
 
 __NOTE__ MLX format is usable for M-chip series of Apple.
 

weights.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8cf69274b0bf234188bd40fe3b66ab312b93b0d7ec05931a89b797273b56093
+oid sha256:e04f7f9932607eb345ecf7f277bf1fc9f68fee866af194f42389138eab7bfa9e
 size 148755675