updated audio model type

app.py

@@ -1,7 +1,7 @@
 import streamlit as st
 import time
 from transformers import pipeline
-from datasets import load_dataset, Audio
+from datasets import load_dataset, Audio, Features
 
 st.set_page_config(page_title="🤗 Transformers Library examples",layout="wide")
 
@@ -156,19 +156,6 @@ def audio_classification():
 
 # function forAutomatic Speech Recognition model
 def automatic_speech_recognition():
-    minds = load_dataset("PolyAI/minds14", name="en-US", split="train")
-    minds = minds.train_test_split(test_size=0.2)
-    st.write(minds)
-    minds = minds.remove_columns(["path", "transcription", "english_transcription", "lang_id"])
-    st.write("minds[train][0] " , minds["train"][0])
-    labels = minds["train"].features["intent_class"].names
-    st.write("labels " ,labels)
-    label2id, id2label = dict(), dict()
-    for i, label in enumerate(labels):
-        label2id[label] = str(i)
-        id2label[str(i)] = label
-    st.write("label2id - id2label" , label2id , id2label)
-
     code = '''
             from transformers import pipeline
 
@@ -177,12 +164,14 @@ def automatic_speech_recognition():
         '''
     st.code(code, language='python')
     if st.button("Run Test ", type="primary"):
+        speech_recognizer = pipeline("automatic-speech-recognition", model="facebook/wav2vec2-base-960h")
+        dataset = load_dataset("PolyAI/minds14", name="en-US", split="train")
+        dataset = dataset.cast_column("audio", Audio(sampling_rate=speech_recognizer.feature_extractor.sampling_rate))
+        result = speech_recognizer(dataset[:4]["audio"])
         with st.spinner('Wait for it...'):
             time.sleep(5)
-        transcriber = pipeline(task="automatic-speech-recognition")
-        results = transcriber("./data/audio.m4a")
         st.write("Output:")
-        st.success(results)
+        st.success([d["text"] for d in result])
 
 
 # function for Image Captioningn model