Update app.py

app.py

@@ -1,19 +1,20 @@
 import gradio as gr
-from transformers import AutoProcessor, BarkModel
-import scipy
+from transformers import VitsModel, AutoTokenizer
 import torch
+import scipy.io.wavfile as wavfile
 
-processor = AutoProcessor.from_pretrained("suno/bark-small")
-model = BarkModel.from_pretrained("suno/bark-small")
+model = VitsModel.from_pretrained("facebook/mms-tts-eng")
+tokenizer = AutoTokenizer.from_pretrained("facebook/mms-tts-eng")
+
+text = "some example text in the English language"
 
 def greet(text):
-    inputs = processor(
-        text=[text],
-        return_tensors="pt",
-    )
-    speech_values = model.generate(**inputs, do_sample=True, num_beams=5)
-    scipy.io.wavfile.write("tmp.wav", rate=24000, data=speech_values.cpu().numpy().squeeze())
-    return open("tmp.wav", "rb").read()
+    inputs = tokenizer(text, return_tensors="pt")
+    with torch.no_grad():
+        output = model(**inputs).waveform
+        out = output[0]
+        wavfile.write("tmp.wav", rate=16000, data=out)
+        return open("tmp.wav", "rb").read()
 
 iface = gr.Interface(fn=greet, inputs="text", outputs="audio")
 iface.launch()