Update app.py

app.py

@@ -1,7 +1,7 @@
 import gradio as gr
 from transformers import pipeline, WhisperProcessor, WhisperForConditionalGeneration
 import torch
-from datasets import load_dataset
+import soundfile as sf
 
 # Load Whisper model and processor
 processor = WhisperProcessor.from_pretrained("openai/whisper-large")
@@ -12,12 +12,11 @@ emotion_classifier = pipeline("text-classification", model="SamLowe/roberta-base
 
 # Define a function to process audio and analyze emotions
 def transcribe_and_analyze(audio_path):
-    # Load audio
-    dataset = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
-    audio = dataset[0]["audio"]["array"]
-
+    # Load audio from the provided file
+    audio, sample_rate = sf.read(audio_path)
+    
     # Process audio with Whisper
-    input_features = processor(audio, return_tensors="pt").input_features
+    input_features = processor(audio, sampling_rate=sample_rate, return_tensors="pt").input_features
     predicted_ids = model.generate(input_features)
     transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]