def main(): print('Initializing Training Process..') parser = argparse.ArgumentParser() parser.add_argument('--group_name', default=None) parser.add_argument('--input_wavs_dir', default='LJSpeech-1.1/wavs', help='') parser.add_argument('--input_mels_dir', default='ft_dataset', help='') parser.add_argument('--input_training_file', default='LJSpeech-1.1/training.txt', help='') parser.add_argument('--input_validation_file', default='LJSpeech-1.1/validation.txt', help='') parser.add_argument('--checkpoint_path', default='cp_hifigan') parser.add_argument('--config', default='') parser.add_argument('--training_epochs', default=3100, type=int) parser.add_argument('--stdout_interval', default=5, type=int) parser.add_argument('--checkpoint_interval', default=5000, type=int) parser.add_argument('--summary_interval', default=100, type=int) parser.add_argument('--validation_interval', default=1000, type=int) parser.add_argument('--fine_tuning', default=False, type=bool) a = parser.parse_args() with open(a.config) as f: data = f.read() json_config = json.loads(data) h = AttrDict(json_config) build_env(a.config, 'config.json', a.checkpoint_path) torch.manual_seed(h.seed) if torch.cuda.is_available(): torch.cuda.manual_seed(h.seed) h.num_gpus = torch.cuda.device_count() h.batch_size = int(h.batch_size / h.num_gpus) print('Batch size per GPU :', h.batch_size) else: pass if h.num_gpus > 1: mp.spawn(train, nprocs=h.num_gpus, args=( a, h, )) else: train(0, a, h)
def main(): parser = argparse.ArgumentParser() parser.add_argument('--group_name', default=None) parser.add_argument('--input_wavs_dir', default='LJSpeech-1.1/wavs') parser.add_argument('--input_validation_file', default='LJSpeech-1.1/validation.txt') parser.add_argument('--checkpoint_path', default='cp_hifigan') parser.add_argument('--config', default='') parser.add_argument('--fine_tuning', default=False, type=bool) parser.add_argument('--input_mels_dir', default='ft_dataset') parser.add_argument('--speakers_json', default=None, type=str) parser.add_argument('--batch_size', default=15, type=int) # for train script compatibility parser.add_argument('--input_training_file', default='LJSpeech-1.1/training.txt') a = parser.parse_args() with open(a.config) as f: data = f.read() if a.speakers_json: with open(a.speakers_json) as f: speaker_mapping = json.load(f) else: speaker_mapping = None json_config = json.loads(data) h = AttrDict(json_config) torch.manual_seed(h.seed) if torch.cuda.is_available(): torch.cuda.manual_seed(h.seed) h.num_gpus = torch.cuda.device_count() h.batch_size = int(h.batch_size / h.num_gpus) print('Batch size per GPU :', h.batch_size) else: pass h.segment_size = h.segment_size*8 eval(0, a, h, speaker_mapping)
def main(): print('Initializing the Training Process..') parser = argparse.ArgumentParser() parser.add_argument('--input_wavs_dir', default='data/recordings') parser.add_argument('--input_mels_dir', default='processed_spokenDigits_np') parser.add_argument('--config', default='processed_spokenDigits_np') parser.add_argument('--training_epochs', default='1000') a = parser.parse_args() with open(a.config) as f: data = f.read() json_config = json.loads(data) h = AttrDict(json_config) build_env(a.config, 'config.json', a.checkpoint_path) torch.manual_seed(h.seed): if torch.cuda.is_availale(h.seed): torch.cuda.manual_seeed(h.seed) h.batch_size = int(h.batch_size / h.num_gpu) else: print('\nRunning on cpu') # train now-- g_losses, d_losses, generated_mels = train(h) # visualize the loss as the network trained plt.plot(g_losses, d_losses) plt.xlabel('100\'s of batches') plt.ylabel('loss') plt.grid(True) # plt.ylim(0, 2.5) # consistent scale plt.show()