Update functions.py

functions.py

@@ -30,6 +30,7 @@ margin-bottom: 2.5rem">{}</div> """
 @st.experimental_singleton(suppress_st_warning=True)
 def load_models():
     asr_model = whisper.load_model("small")
+    asr_pipe = pipeline("automatice-speech-recognition",model = "openai/whisper-large")
     q_model = ORTModelForSequenceClassification.from_pretrained("nickmuchi/quantized-optimum-finbert-tone")
     ner_model = AutoModelForTokenClassification.from_pretrained("xlm-roberta-large-finetuned-conll03-english")
     q_tokenizer = AutoTokenizer.from_pretrained("nickmuchi/quantized-optimum-finbert-tone")
@@ -40,7 +41,7 @@ def load_models():
     sbert = SentenceTransformer("all-mpnet-base-v2")
     cross_encoder = CrossEncoder('cross-encoder/ms-marco-MiniLM-L-12-v2')
     
-    return asr_model, sent_pipe, sum_pipe, ner_pipe, sbert, cross_encoder
+    return asr_pipe, sent_pipe, sum_pipe, ner_pipe, sbert, cross_encoder
 
 @st.experimental_singleton(suppress_st_warning=True)
 def get_spacy():
@@ -56,15 +57,14 @@ def inference(link, upload):
       yt = YouTube(link)
       title = yt.title
       path = yt.streams.filter(only_audio=True)[0].download(filename="audio.mp4")
-      options = whisper.DecodingOptions(without_timestamps=True)
-      results = asr_model.transcribe(path)
+      results = asr_pipe(path)
       
-      return results, yt.title
+      return results['text'], yt.title
       
     elif upload:
-      results = asr_model.transcribe(upload)
+      results = asr_pipe(upload)
       
-      return results, "Transcribed Earnings Audio"
+      return results['text'], "Transcribed Earnings Audio"
 
 @st.experimental_memo(suppress_st_warning=True)       
 def chunk_long_text(text,threshold):