Intel
/

whisper-base-onnx-int4-inc

Automatic Speech Recognition

Intel® Neural Compressor

neural-compressor

Inference Endpoints

Model card Files Files and versions Community

yuwenz commited on Oct 9, 2023

Commit

97fe3a6

·

1 Parent(s): 2f84176

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -130,7 +130,7 @@ print(f"Result wer: {wer_result * 100}")
 ```
 ## Metrics (Model Performance):
-| Model  | Model Size (GB) | wer |
 |---|:---:|:---:|
-| FP32 |0.65|5.04|
-| INT4 |0.28|6.14|

 ```
 ## Metrics (Model Performance):
+| Model  | Model Size (MB) | wer |
 |---|:---:|:---:|
+| FP32 |465|5.04|
+| INT4 |289|6.14|