Update app.py

app.py

@@ -4,32 +4,22 @@ import transformers
 #  predictions = pipeline(image)
  #  return {p["label"]: p["score"] for p in predictions}
 
-from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
 from datasets import load_dataset
 import torch
- 
+ from transformers import pipeline
+
 def predict(speech):
  # load model and tokenizer
-   processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-base-960h")
-   model = Wav2Vec2ForCTC.from_pretrained("facebook/wav2vec2-base-960h")
- 
-   #pipeline = pipeline(task="speech-classification", model="facebook/wav2vec2-base-960h")
-     
- # load dummy dataset and read soundfiles
-   ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
- 
- # tokenize
-   input_values = processor(ds[0]["audio"]["array"], return_tensors="pt", padding="longest").input_values  # Batch size 1
- 
- # retrieve logits
-   logits = model(input_values).logits
- 
- # take argmax and decode
-   predicted_ids = torch.argmax(logits, dim=-1)
-   transcription = processor.batch_decode(predicted_ids)
-   return transcription
+   torch.manual_seed(42)
+   ds = load_dataset("hf-internal-testing/librispeech_asr_demo", "clean", split="validation")
+   audio_file = ds[0]["audio"]["path"]
+   audio_classifier = pipeline(
+    task="audio-classification", model="ehcalabres/wav2vec2-lg-xlsr-en-speech-emotion-recognition"
+    preds = audio_classifier(audio_file)
+    preds = [{"score": round(pred["score"], 4), "label": pred["label"]} for pred in preds]
+   return preds
    
-demo = gr.Interface(fn=predict  outputs="label")
+demo = gr.Interface(fn=predict, inputs='texts'  outputs="texts")
 
 demo.launch()