Update app.py

app.py

@@ -17,22 +17,22 @@ from convert2list import convert_to_list
 from processDoubles import process_doubles
 from replaceWords import replace_words
 
-transcriber = pipeline(task="automatic-speech-recognition", model="cdactvm/w2v-bert-2.0-hindi_v1")
-processor = AutoProcessor.from_pretrained("cdactvm/w2v-bert-2.0-hindi_v1")
+# transcriber = pipeline(task="automatic-speech-recognition", model="cdactvm/w2v-bert-2.0-hindi_v1")
+# processor = AutoProcessor.from_pretrained("cdactvm/w2v-bert-2.0-hindi_v1")
 
-vocab_dict = processor.tokenizer.get_vocab()
+# vocab_dict = processor.tokenizer.get_vocab()
 
-sorted_vocab_dict = {k.lower(): v for k, v in sorted(vocab_dict.items(), key=lambda item: item[1])}
-decoder = build_ctcdecoder(
-    labels=list(sorted_vocab_dict.keys()),
-    kenlm_model_path="lm.binary",
-    )
-processor_with_lm = Wav2Vec2ProcessorWithLM(
-    feature_extractor=processor.feature_extractor,
-    tokenizer=processor.tokenizer,
-    decoder=decoder
-    )
-processor.feature_extractor._processor_class = "Wav2Vec2ProcessorWithLM"
+# sorted_vocab_dict = {k.lower(): v for k, v in sorted(vocab_dict.items(), key=lambda item: item[1])}
+# decoder = build_ctcdecoder(
+#     labels=list(sorted_vocab_dict.keys()),
+#     kenlm_model_path="lm.binary",
+#     )
+# processor_with_lm = Wav2Vec2ProcessorWithLM(
+#     feature_extractor=processor.feature_extractor,
+#     tokenizer=processor.tokenizer,
+#     decoder=decoder
+#     )
+# processor.feature_extractor._processor_class = "Wav2Vec2ProcessorWithLM"
 
  
 def transcribe(audio):