Rename audio_generation.py to AudioGeneration.py

AudioGeneration.py

@@ -0,0 +1,9 @@
+from TTS.api import TTS
+
+# Load the model once
+tts_model = TTS(model_name="tts_models/en/ljspeech/tacotron2-DDC", progress_bar=False, gpu=False)
+
+def generate_audio(text, filename):
+    output_path = filename
+    tts_model.tts_to_file(text=text, file_path=output_path)
+    return output_path

audio_generation.py

@@ -1,40 +0,0 @@
-# audio_generation.py 
-
-from transformers import AutoProcessor, BarkModel
-import torch
-import numpy as np
-from scipy.io.wavfile import write as write_wav
-from pydub import AudioSegment
-import os
-import uuid
-
-processor = AutoProcessor.from_pretrained("suno/bark")
-model = BarkModel.from_pretrained("suno/bark")
-
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model.to(device)
-
-def split_text(text, max_len=150):
-    return [text[i:i+max_len] for i in range(0, len(text), max_len)]
-
-def generate_audio(text, output_dir="audios"):
-    os.makedirs(output_dir, exist_ok=True)
-    chunks = split_text(text)
-    final_audio = AudioSegment.empty()
-
-    for idx, chunk in enumerate(chunks):
-        inputs = processor(chunk, return_tensors="pt").to(device)
-        audio_array = model.generate(**inputs)
-        audio_array = audio_array.cpu().numpy().squeeze()
-        audio_array = audio_array / np.max(np.abs(audio_array))
-
-        temp_path = os.path.join(output_dir, f"{uuid.uuid4()}.wav")
-        write_wav(temp_path, rate=22050, data=audio_array)
-
-        segment = AudioSegment.from_wav(temp_path)
-        final_audio += segment
-        os.remove(temp_path)
-
-    final_filename = os.path.join(output_dir, f"{uuid.uuid4()}_final.wav")
-    final_audio.export(final_filename, format="wav")
-    return final_filename