wav2vec2-base-turkish / my_conf.yaml
ceyda's picture
add fs conf & custom datasetted code
fcf1d1f
# @package _group_
common:
tpu: true
fp16: false
log_format: json
log_interval: 10
wandb_project: pretrain_tpu_960h
checkpoint:
save_interval_updates: 500
keep_interval_updates: 2
no_epoch_checkpoints: false
task:
_name: audio_pretraining
data: ???
max_sample_size: 257600
min_sample_size: 46400
normalize: false
num_batch_buckets: 3
precompute_mask_indices: true
enable_padding: true
dataset:
num_workers: 12
max_tokens: 1200000
skip_invalid_size_inputs_valid_test: true
distributed_training:
distributed_world_size: 8
ddp_backend: legacy_ddp
criterion:
_name: wav2vec
infonce: true
log_keys: ["prob_perplexity","code_perplexity","temp"]
loss_weights: [0.1, 0]
optimization:
max_update: 400000
lr: [0.0005]
optimizer:
_name: adam
adam_betas: (0.9,0.98)
adam_eps: 1e-06
weight_decay: 0.01
lr_scheduler:
_name: polynomial_decay
warmup_updates: 32000
model:
_name: wav2vec2
quantize_targets: true
final_dim: 256
encoder_layerdrop: 0.05
dropout_input: 0.1
dropout_features: 0.1
feature_grad_mult: 0.1
encoder_embed_dim: 768