Update app.py

app.py

@@ -9,6 +9,7 @@ from transformers import SpeechT5Processor, SpeechT5ForTextToSpeech, SpeechT5Hif
 from speechbrain.pretrained import EncoderClassifier
 from datasets import load_dataset
 from huggingface_hub import hf_hub_download
+import uuid
 
 
 from piper import PiperVoice
@@ -25,7 +26,9 @@ config_path = hf_hub_download(repo_id="fahadqazi/piper-sindhi", filename="model.
 
 voice = PiperVoice.load(model_path=model_path, config_path=config_path, use_cuda=device=="cuda")
 
-
+synthesize_args = {
+    "speaker_id": 0,
+}
 
 
 def load_models_and_data():
@@ -139,8 +142,10 @@ def text_to_speech(text, audio_file=None):
 
     # return (16000, speech_np)
 
-    # Generate speech
-    audio = tts.synthesize(normalized_text)
+    # Generate speech: Write to file
+    output_file = f"{uuid.uuid4()}.wav"
+    with wave.open(output_file, "wb") as wav_file:
+        voice.synthesize(normalized_text, wav_file, **synthesize_args)
     
     # Save the audio to a file
     # with open("output.wav", "wb") as f:
@@ -148,7 +153,7 @@ def text_to_speech(text, audio_file=None):
 
     # return audio_file
 
-    return audio
+    return output_file
 
     
 iface = gr.Interface(