Upload 2 files

app.py

@@ -3,7 +3,6 @@ import streamlit as st
 import time
 import os
 
-
 os.environ['COQUI_TOS_AGREED'] = '1'
 os.environ['BARK_TOS_AGREED'] = '1'
 
@@ -19,11 +18,9 @@ def model_coqui():
 
 # @st.cache_resource()
 def model_bark():
-    from transformers import AutoProcessor, BarkModel
-    processor = AutoProcessor.from_pretrained("suno/bark")
-    model = BarkModel.from_pretrained("suno/bark")
-
-    return processor, model
+    device = "cpu"
+    tts = TTS("tts_models/multilingual/multi-dataset/bark").to(device)
+    return tts
 
 
 col1, col2 = st.columns(2)
@@ -59,19 +56,14 @@ if speaker:
         st.audio(output_path_coqui, format="audio/mp3")
 
     with col22:
+        tts_bark = model_bark()
+        speaker_wav_2 = "speaker_embeddings/tr_speaker_0"
 
-        processor, model = model_bark()
-        voice_preset = "tr_speaker_1"
-        inputs = processor(f"{sentence}", voice_preset=voice_preset)
-
-        start_time_bark = time.time()  # Start the timer
-        audio_array = model.generate(**inputs)
-        end_time = time.time()  # End the timer
-
-        audio_array = audio_array.cpu().numpy().squeeze()
-        sample_rate = model.generation_config.sample_rate
+        start_time_bark = time.time()
+        output_path_bark = tts_bark.tts_to_file(text=sentence, speaker_wav=speaker_wav_2)
+        end_time = time.time()
 
-        execution_time = round(end_time - start_time_bark,2)  # Calculate the time taken
-        st.write(f"Bark için tamamlanma süresi: {execution_time} saniye")  # Display the time taken
+        execution_time = round(end_time - start_time_bark,2)
+        st.write(f"Bark içi tamamlanma süresi: {execution_time} saniye")
 
-        st.audio(audio_array, format="audio/wav", sample_rate=sample_rate)
+        st.audio(output_path_bark, format="audio/mp3")

requirements.txt

@@ -1,3 +1,3 @@
 streamlit
-TTS
-torch
+git+https://github.com/coqui-ai/TTS
+torch