Update app.py

app.py

@@ -45,7 +45,9 @@ speakers = {
 }
 
 def generateAudio(text_to_audio, s3_save_as):
-
+    
+    s3_save_as = '-'.join(save_as.split()) + ".wav"
+    
     def cut_text(text, max_tokens=500):
         # Remove non-alphanumeric characters, except periods and commas
         text = re.sub(r"[^\w\s.,]", "", text)
@@ -57,14 +59,14 @@ def generateAudio(text_to_audio, s3_save_as):
         cut = ' '.join(tokens[:max_tokens])
         return cut
 
-    def save_audio_to_s3(audio, filename):
+    def save_audio_to_s3(audio):
         # Create an instance of the S3 client
         s3 = boto3.client('s3',
                           aws_access_key_id=AWS_ACCESS_KEY_ID,
                           aws_secret_access_key=AWS_SECRET_ACCESS_KEY)
 
         # Full path of the file in the bucket
-        s3_key = "public/" + filename
+        s3_key = "public/" + s3_save_as
 
         # Upload the audio file to the S3 bucket
         s3.upload_fileobj(audio, S3_BUCKET_NAME, s3_key)
@@ -84,14 +86,7 @@ def generateAudio(text_to_audio, s3_save_as):
         # generate speech with the models
         speech = model.generate_speech(
             inputs["input_ids"], speaker_embeddings, vocoder=vocoder)
-        if speaker is not None:
-            # if we have a speaker, we use the speaker's ID in the filename
-            output_filename = f"{speaker}-{'-'.join(text.split()[:6])}.wav"
-        else:
-            # if we don't have a speaker, we use a random string in the filename
-            random_str = ''.join(random.sample(
-                string.ascii_letters+string.digits, k=5))
-            output_filename = f"{random_str}-{'-'.join(text.split()[:6])}.wav"
+        
         # create BytesIO object to store the audio
         audio_buffer = BytesIO()
         # save the generated speech to the BytesIO buffer
@@ -99,14 +94,12 @@ def generateAudio(text_to_audio, s3_save_as):
         audio_buffer.seek(0)
 
         # Save the audio to S3
-        save_audio_to_s3(audio_buffer, output_filename)
-
-        # return the filename for reference
-        return output_filename
-
-    output_filename = save_text_to_speech(text_to_audio, "clb")
+        save_audio_to_s3(audio_buffer)
 
-    return f"Saved {output_filename}"
+    save_text_to_speech(text_to_audio, 2271)
+    return s3_save_as
+    
 
-iface = gr.Interface(fn=generateAudio, inputs=[Textbox(label="text_to_audio"), Textbox(label="s3_save_as")], outputs="text")
+iface = gr.Interface(fn=generateAudio, inputs=[Textbox(label="text_to_audio"), Textbox(label="
+")], outputs="text")
 iface.launch()