Update README.md

README.md

@@ -13,13 +13,13 @@ license: apache-2.0
 This model is a distilled version of the wav2vec2 model (https://arxiv.org/pdf/2006.11477.pdf). This model is 45% times smaller and 3 times faster than the original wav2vec2 base model.
 
 # Evaluation results
-This model achieves the following results : 
+This model achieves the following results (speed is mesured for a batch size of 64): 
 
-|Model| Size| WER Librispeech-test-clean |WER Librispeech-test-other| 
-|----------| ------------- |-------------|-----------| 
-|Distil-wav2vec2| 197.9 Mb | 0.0983 | 0.2266|
-|wav2vec2-base| 360 Mb | 0.0389 | 0.1047|
+|Model| Size| WER Librispeech-test-clean |WER Librispeech-test-other|Speed on cpu|speed on gpu| 
+|----------| ------------- |-------------|-----------| ------|----|
+|Distil-wav2vec2| 197.9 Mb | 0.0983 | 0.2266|0.4006s| 0.0082s|
+|wav2vec2-base| 360 Mb | 0.0389 | 0.1047|	0.4919s|0.0046s |
 
 
 # Usage
-notebook (google colab) at https://github.com/OthmaneJ/distil-wav2vec2
+notebook (executes seamlessly on google colab) at https://github.com/OthmaneJ/distil-wav2vec2