Update README.md

README.md

@@ -83,9 +83,12 @@ For the evaluation, you can use the code below. Ensure your dataset to be in fol
 |:----:|:--------:|
 | path/to/audio_file.wav | "TRANSCRIPTION" |
 
+also, make sure you have installed `pip install jiwer` prior to running.
+
 ```python
-import torch
+import tensorflow
 import torchaudio
+import torch
 import librosa
 from datasets import load_dataset,load_metric
 import numpy as np
@@ -129,11 +132,11 @@ print("WER: {:.2f}".format(100 * wer.compute(predictions=result["prediction"], r
 print("CER: {:.2f}".format(100 * cer.compute(predictions=result["prediction"], references=result["reference"])))
 ```
 
-*Result (WER)*:
+*Result (WER) on common-voice 6.1*:
 
-| clean | other |
-|---|---|
-| 6.0 | 16.4 |
+| cleaned | other |
+|:---:|:---:|
+| 0.06 | 0.16 |
 
 
 ## Citation