Add gc.collect()

TTS/demos/xtts_ft_demo/utils/formatter.py

@@ -1,4 +1,5 @@
 import os
+import gc
 import torchaudio
 import pandas
 from faster_whisper import WhisperModel
@@ -152,7 +153,8 @@ def format_audio_list(audio_files, target_language="en", out_path=None, buffer=0
     df_eval = df_eval.sort_values('audio_file')
     df_eval.to_csv(eval_metadata_path, sep="|", index=False)
 
-    # deallocate VRAM
+    # deallocate VRAM and RAM
     del asr_model, df_train, df_eval, df, metadata
+    gc.collect()
 
     return train_metadata_path, eval_metadata_path, audio_total_size

TTS/demos/xtts_ft_demo/utils/gpt_train.py

@@ -1,4 +1,5 @@
 import os
+import gc
 
 from trainer import Trainer, TrainerArgs
 
@@ -164,7 +165,8 @@ def train_gpt(language, num_epochs, batch_size, grad_acumm, train_csv, eval_csv,
 
     trainer_out_path = trainer.output_path
 
-    # deallocate VRAM
+    # deallocate VRAM and RAM
     del model, trainer, train_samples, eval_samples
+    gc.collect()
 
     return XTTS_CONFIG_FILE, XTTS_CHECKPOINT, TOKENIZER_FILE, trainer_out_path, speaker_ref