updated readme

README.md

@@ -76,8 +76,9 @@ import numpy as np
 import re
 
 wer = load_metric("wer")
-processor = Wav2Vec2Processor.from_pretrained(output_models_dir)
-model = Wav2Vec2ForCTC.from_pretrained(output_models_dir+'/'+checkpoint)
+processor = Wav2Vec2Processor.from_pretrained("tanmaylaud/wav2vec2-large-xlsr-hindi-marathi")
+model = Wav2Vec2ForCTC.from_pretrained("tanmaylaud/wav2vec2-large-xlsr-hindi-marathi")
+
 model.to("cuda")
 
 chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\”\�\।]'
@@ -90,7 +91,7 @@ def speech_file_to_array_fn(batch):
     batch["speech"] = speech_array[0].numpy()
     batch["sampling_rate"] = sampling_rate
     batch["target_text"] = batch["sentence"]
-    batch["speech"] = librosa.resample(np.asarray(batch["speech"]), 8_000, 16_000)
+    batch["speech"] = librosa.resample(np.asarray(batch["speech"]), sampling_rate, 16_000)
     batch["sampling_rate"] = 16_000
     return batch
 
@@ -109,4 +110,6 @@ def evaluate(batch):
 
 result = test.map(evaluate, batched=True, batch_size=32)
 print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["text"])))
-```
+```
+
+Link to eval notebook : https://colab.research.google.com/drive/1nZRTgKfxCD9cvy90wikTHkg2il3zgcqW#scrollTo=cXWFbhb0d7DT