parler-tts/helpers/training_configs/starting_point_0.01.json

{
    "model_name_or_path": "./parler-tts-untrained-600M/parler-tts-untrained-600M/",
    "save_to_disk":  "./tmp_dataset_audio/",
    "temporary_save_to_disk": "./audio_code_tmp/",


    "feature_extractor_name":"ylacombe/dac_44khZ_8kbps",
    "description_tokenizer_name":"google/flan-t5-base",
    "prompt_tokenizer_name":"google/flan-t5-base",

    "report_to": ["wandb"],
    "overwrite_output_dir": true,
    "output_dir": "./output_dir_training",

    "train_dataset_name": "blabble-io/libritts_r+blabble-io/libritts_r+blabble-io/libritts_r+parler-tts/mls_eng_10k",
    "train_metadata_dataset_name": "parler-tts/libritts_r_tags_tagged_10k_generated+parler-tts/libritts_r_tags_tagged_10k_generated+parler-tts/libritts_r_tags_tagged_10k_generated+parler-tts/mls-eng-10k-tags_tagged_10k_generated",
    "train_dataset_config_name": "clean+clean+other+default",
    "train_split_name": "train.clean.360+train.clean.100+train.other.500+train",

    "eval_dataset_name": "blabble-io/libritts_r+parler-tts/mls_eng_10k",
    "eval_metadata_dataset_name": "parler-tts/libritts_r_tags_tagged_10k_generated+parler-tts/mls-eng-10k-tags_tagged_10k_generated",
    "eval_dataset_config_name": "other+default",
    "eval_split_name": "test.other+test",

    "target_audio_column_name": "audio", 
    "description_column_name": "text_description",
    "prompt_column_name": "text",

    "max_eval_samples": 96,
    
    "max_duration_in_seconds": 30,
    "min_duration_in_seconds": 2.0,
    "max_text_length": 400,

    "group_by_length": true,

    "add_audio_samples_to_wandb": true,
    "id_column_name": "id",

    "preprocessing_num_workers": 8,

    "do_train": true,
    "num_train_epochs": 40,
    "gradient_accumulation_steps": 8,
    "gradient_checkpointing": false,
    "per_device_train_batch_size": 3,
    "learning_rate": 0.00095,
    "adam_beta1": 0.9,
    "adam_beta2": 0.99,
    "weight_decay": 0.01,

    "lr_scheduler_type": "constant_with_warmup",
    "warmup_steps":  20000,


    "logging_steps": 1000,
    "freeze_text_encoder": true,


    "do_eval": true, 
    "predict_with_generate": true,
    "include_inputs_for_metrics": true,
    "evaluation_strategy": "steps",
    "eval_steps": 10000,
    "save_steps": 10000,

    "per_device_eval_batch_size": 12,

    "audio_encoder_per_device_batch_size":20,
    "dtype": "bfloat16",
    "seed": 456,

    "dataloader_num_workers":8
}