Update app.py

app.py

@@ -1,8 +1,24 @@
 import gradio as gr
-from transformers import pipeline
+from transformers import pipeline, VitsModel, AutoTokenizer, set_seed
+import torch
+import uuid
+import scipy.io.wavfile as wav
 
-get_completion = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
 
+generate_summary = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
+tts_model = VitsModel.from_pretrained("facebook/mms-tts-eng")
+tts_tokenizer = AutoTokenizer.from_pretrained("facebook/mms-tts-eng")
+
+def gen_speech(text):
+    set_seed(555)  # Make it deterministic
+    input_text = tts_tokenizer(text, return_tensors="pt")
+    with torch.no_grad():
+        outputs = tts_model(**input_text)
+    waveform_np = outputs.waveform[0].cpu().numpy()
+    output_file = f"{str(uuid.uuid4())}.wav"
+    wav.write(output_file, rate=tts_model.config.sampling_rate, data=waveform_np)
+    return output_file
+    
 def translate(input_text, source, target):
     # source_readable = source
     # if source == "Auto Detect" or source.startswith("Detected"):
@@ -20,14 +36,19 @@ def translate(input_text, source, target):
       return "", f"Error: Translation direction {source_readable} to {target} is not supported by Helsinki Translation Models"
 
 def summarize(input):
-    output = get_completion(input)
+    output = generate_summary(input)
     summary_origin = output[0]['summary_text']
     summary_translated = translate(summary_origin,'en','fr')
-    return summary_origin, summary_translated[0]
+    audio_output_filepath = gen_speech(summary_origin)
+    return summary_origin, summary_translated[0], audio_output_filepath
 
 demo = gr.Interface(fn=summarize, 
                     inputs=[gr.Textbox(label="Text to summarize", lines=6)],
-                    outputs=[gr.Textbox(label="Result", lines=3),gr.Textbox(label="Translate Result", lines=3)],
+                    outputs=[
+                        gr.Textbox(label="Result", lines=3),
+                        gr.Textbox(label="Translate Result", lines=3),
+                        gr.Audio(type="filepath", label="Generated Speech")
+                    ],
                     title="Text summarization with distilbart-cnn",
                     description="Summarize any text using the `sshleifer/distilbart-cnn-12-6` model under the hood!",
                     examples=[