Update app.py

app.py

@@ -6,6 +6,7 @@ import numpy as np
 from bark.generation import preload_models, SAMPLE_RATE
 from bark import generate_audio
 from scipy.io import wavfile
+from IPython.display import Audio
 import gradio as gr
 nltk.download('punkt')
 os.environ["CUDA_VISIBLE_DEVICES"] = "0"
@@ -13,47 +14,179 @@ preload_models()
 
 
 
-def generate_audio_from_text(text,language_prompt,gender_prompt):
+def generate_audio_from_text(text,language_prompt,speaker_prompt):
     if language_prompt == "english":
-        if gender_prompt == "male":
-            history_prompt = "v2/en_speaker_8"
+        if speaker_prompt=="speaker 1":
+            history_prompt = "v2/en_speaker_0"
+        elif speaker_prompt=="speaker 2":
+          history_prompt = "v2/en_speaker_1"
+        elif speaker_prompt=="speaker 3":
+          history_prompt = "v2/en_speaker_2"
+        elif speaker_prompt=="speaker 4":
+          history_prompt = "v2/en_speaker_3"
+        elif speaker_prompt=="speaker 5":
+          history_prompt = "v2/en_speaker_4"
+        elif speaker_prompt=="speaker 6":
+          history_prompt = "v2/en_speaker_5"
+        elif speaker_prompt=="speaker 7":
+          history_prompt = "v2/en_speaker_6"
+        elif speaker_prompt=="speaker 8":
+          history_prompt = "v2/en_speaker_7"
+        elif speaker_prompt=="speaker 9":
+          history_prompt = "v2/en_speaker_8"
+        elif speaker_prompt=="speaker 10":
+          history_prompt = "v2/en_speaker_9"
         else:
             history_prompt = "v2/en_speaker_9"
+
     elif language_prompt == "french":
-        if gender_prompt == "male":
-            history_prompt = "v2/fr_speaker_0"
+        if speaker_prompt=="speaker 1":
+          history_prompt = "v2/fr_speaker_0"
+        elif speaker_prompt=="speaker 2":
+          history_prompt = "v2/fr_speaker_1"
+        elif speaker_prompt=="speaker 3":
+          history_prompt = "v2/fr_speaker_2"
+        elif speaker_prompt=="speaker 4":
+          history_prompt = "v2/fr_speaker_3"
+        elif speaker_prompt=="speaker 5":
+          history_prompt = "v2/fr_speaker_4"
+        elif speaker_prompt=="speaker 6":
+          history_prompt = "v2/fr_speaker_5"
+        elif speaker_prompt=="speaker 7":
+          history_prompt = "v2/fr_speaker_6"
+        elif speaker_prompt=="speaker 8":
+          history_prompt = "v2/fr_speaker_7"
+        elif speaker_prompt=="speaker 9":
+          history_prompt = "v2/fr_speaker_8"
+        elif speaker_prompt=="speaker 10":
+          history_prompt = "v2/fr_speaker_9"
         else:
-            history_prompt = "v2/fr_speaker_1"
+            history_prompt = "v2/fr_speaker_9"
+
     elif language_prompt =="german":
-        if gender_prompt=="male":
-            history_prompt = "v2/de_speaker_2"
+        if speaker_prompt=="speaker 1":
+          history_prompt = "v2/de_speaker_0"
+        elif speaker_prompt=="speaker 2":
+          history_prompt = "v2/de_speaker_1"
+        elif speaker_prompt=="speaker 3":
+          history_prompt = "v2/de_speaker_2"
+        elif speaker_prompt=="speaker 4":
+          history_prompt = "v2/de_speaker_3"
+        elif speaker_prompt=="speaker 5":
+          history_prompt = "v2/de_speaker_4"
+        elif speaker_prompt=="speaker 6":
+          history_prompt = "v2/de_speaker_5"
+        elif speaker_prompt=="speaker 7":
+          history_prompt = "v2/de_speaker_6"
+        elif speaker_prompt=="speaker 8":
+          history_prompt = "v2/de_speaker_7"
+        elif speaker_prompt=="speaker 9":
+          history_prompt = "v2/de_speaker_8"
+        elif speaker_prompt=="speaker 10":
+          history_prompt = "v2/de_speaker_9"
         else:
-            history_prompt="v2/de_speaker_3"
+            history_prompt = "v2/de_speaker_9"
+
     elif language_prompt =="hindi":
-        if gender_prompt=="male":
-            history_prompt = "v2/hi_speaker_8"
+        if speaker_prompt=="speaker 1":
+          history_prompt = "v2/hi_speaker_0"
+        elif speaker_prompt=="speaker 2":
+          history_prompt = "v2/hi_speaker_1"
+        elif speaker_prompt=="speaker 3":
+          history_prompt = "v2/hi_speaker_2"
+        elif speaker_prompt=="speaker 4":
+          history_prompt = "v2/hi_speaker_3"
+        elif speaker_prompt=="speaker 5":
+          history_prompt = "v2/hi_speaker_4"
+        elif speaker_prompt=="speaker 6":
+          history_prompt = "v2/hi_speaker_5"
+        elif speaker_prompt=="speaker 7":
+          history_prompt = "v2/hi_speaker_6"
+        elif speaker_prompt=="speaker 8":
+          history_prompt = "v2/hi_speaker_7"
+        elif speaker_prompt=="speaker 9":
+          history_prompt = "v2/hi_speaker_8"
+        elif speaker_prompt=="speaker 10":
+          history_prompt = "v2/hi_speaker_9"
         else:
-            history_prompt="v2/hi_speaker_3"
+            history_prompt = "v2/hi_speaker_9"
+
     elif language_prompt =="chinese":
-        if gender_prompt=="male":
-            history_prompt = "v2/zh_speaker_1"
+        if speaker_prompt=="speaker 1":
+          history_prompt = "v2/zh_speaker_0"
+        elif speaker_prompt=="speaker 2":
+          history_prompt = "v2/zh_speaker_1"
+        elif speaker_prompt=="speaker 3":
+          history_prompt = "v2/zh_speaker_2"
+        elif speaker_prompt=="speaker 4":
+          history_prompt = "v2/zh_speaker_3"
+        elif speaker_prompt=="speaker 5":
+          history_prompt = "v2/zh_speaker_4"
+        elif speaker_prompt=="speaker 6":
+          history_prompt = "v2/zh_speaker_5"
+        elif speaker_prompt=="speaker 7":
+          history_prompt = "v2/zh_speaker_6"
+        elif speaker_prompt=="speaker 8":
+          history_prompt = "v2/zh_speaker_7"
+        elif speaker_prompt=="speaker 9":
+          history_prompt = "v2/zh_speaker_8"
+        elif speaker_prompt=="speaker 10":
+          history_prompt = "v2/zh_speaker_9"
         else:
-            history_prompt="v2/zh_speaker_4"
+            history_prompt = "v2/zh_speaker_9"
+
     elif language_prompt =="italian":
-        if gender_prompt=="male":
-            history_prompt = "v2/it_speaker_4"
+        if speaker_prompt=="speaker 1":
+          history_prompt = "v2/it_speaker_0"
+        elif speaker_prompt=="speaker 2":
+          history_prompt = "v2/it_speaker_1"
+        elif speaker_prompt=="speaker 3":
+          history_prompt = "v2/it_speaker_2"
+        elif speaker_prompt=="speaker 4":
+          history_prompt = "v2/it_speaker_3"
+        elif speaker_prompt=="speaker 5":
+          history_prompt = "v2/it_speaker_4"
+        elif speaker_prompt=="speaker 6":
+          history_prompt = "v2/it_speaker_5"
+        elif speaker_prompt=="speaker 7":
+          history_prompt = "v2/it_speaker_6"
+        elif speaker_prompt=="speaker 8":
+          history_prompt = "v2/it_speaker_7"
+        elif speaker_prompt=="speaker 9":
+          history_prompt = "v2/it_speaker_8"
+        elif speaker_prompt=="speaker 10":
+          history_prompt = "v2/it_speaker_9"
         else:
-            history_prompt="v2/it_speaker_7"
+            history_prompt = "v2/it_speaker_9"
+            
     elif language_prompt =="japanese":
-        if gender_prompt=="male":
-            history_prompt = "v2/ja_speaker_2"
+        if speaker_prompt=="speaker 1":
+          history_prompt = "v2/ja_speaker_0"
+        elif speaker_prompt=="speaker 2":
+          history_prompt = "v2/ja_speaker_1"
+        elif speaker_prompt=="speaker 3":
+          history_prompt = "v2/ja_speaker_2"
+        elif speaker_prompt=="speaker 4":
+          history_prompt = "v2/ja_speaker_3"
+        elif speaker_prompt=="speaker 5":
+          history_prompt = "v2/ja_speaker_4"
+        elif speaker_prompt=="speaker 6":
+          history_prompt = "v2/ja_speaker_5"
+        elif speaker_prompt=="speaker 7":
+          history_prompt = "v2/ja_speaker_6"
+        elif speaker_prompt=="speaker 8":
+          history_prompt = "v2/ja_speaker_7"
+        elif speaker_prompt=="speaker 9":
+          history_prompt = "v2/ja_speaker_8"
+        elif speaker_prompt=="speaker 10":
+          history_prompt = "v2/ja_speaker_9"
         else:
-            history_prompt="v2/ja_speaker_0"
+            history_prompt = "v2/ja_speaker_9"
     else:
         raise ValueError("Invalid language or gender selection")
 
     sentences = nltk.sent_tokenize(text)
-    # silence = np.zeros(int(0.25 * SAMPLE_RATE))  # quarter second of silence
+    silence = np.zeros(int(0.25 * SAMPLE_RATE))  # quarter second of silence
 
     pieces = []
     for sentence in sentences:
@@ -83,18 +216,25 @@ language_options = [
 
 ]
 
-gender_options = [
-    "male",
-    "female",
+speaker_options=[
+    "speaker 1",
+    "speaker 2",
+    "speaker 3",
+    "speaker 4",
+    "speaker 5",
+    "speaker 6",
+    "speaker 7",
+    "speaker 8",
+    "speaker 9",
+    "speaker 10",
 ]
-
 # Create a Gradio interface with text input and dropdown menus for language and gender
 iface = gr.Interface(
     fn=generate_audio_from_text,
     inputs=[
         gr.Textbox(text="Enter text to convert to speech:"),
         gr.Dropdown(choices=language_options, label="Select language:"),
-        gr.Dropdown(choices=gender_options, label="Select gender:"),
+        gr.Dropdown(choices=speaker_options, label="Select speaker:"),
     ],
     outputs=gr.outputs.File(label="Download WAV File"),
     title="Text-to-Speech App Vertical Solution",
@@ -102,4 +242,4 @@ iface = gr.Interface(
 )
 
 # Launch the Gradio app with sharing enabled
-iface.launch(debug=True, enable_queue=True)
+iface.launch(share=True, debug=True, enable_queue=True)