Include Sampling Rate

app.py

@@ -43,7 +43,7 @@ def texttoaudio(prompt, neg_prompt, seed, inf_steps, guidance_scale, n_candidate
     return (16000, waveform)
 
 def score_waveforms(text, waveforms):
-    inputs = processor(text=text, audios=list(waveforms), return_tensors="pt", padding=True)
+    inputs = processor(text=text, audios=list(waveforms), return_tensors="pt", padding=True, sampling_rate=16000)
     inputs = {key: inputs[key].to(device) for key in inputs}
     with torch.no_grad():
         logits_per_text = clap_model(**inputs).logits_per_text  # this is the audio-text similarity score