14 languages
multilingual-pl-bert / config.yml
raph30370's picture
Create config.yml
ed1ec88 verified
log_dir: "Checkpoint_all_phonemes"
mixed_precision: "fp16"
data_folder: "wikipedia_20220301.en.processed"
batch_size: 32
save_interval: 20000
log_interval: 10
num_process: 1 # number of GPUs
num_steps: 2000000
dataset_params:
tokenizer: "bert-base-multilingual-cased"
token_separator: " " # token used for phoneme separator (space)
token_mask: "M" # token used for phoneme mask (M)
word_separator: 102 # token used for word separator (<formula>)
token_maps: "token_maps.pkl" # token map path
max_mel_length: 512 # max phoneme length
word_mask_prob: 0.15 # probability to mask the entire word
phoneme_mask_prob: 0.1 # probability to mask each phoneme
replace_prob: 0.2 # probablity to replace phonemes
model_params:
vocab_size: 178
hidden_size: 768
num_attention_heads: 12
intermediate_size: 2048
max_position_embeddings: 512
num_hidden_layers: 12
dropout: 0.1