wehub-resource-sync
ba4be087d5
Create PR to main with cherry-pick from release / cherry-pick (push) Failing after 0s
CICD NeMo / pre-flight (push) Failing after 0s
CICD NeMo / configure (push) Has been skipped
Build, validate, and release Neural Modules / pre-flight (push) Failing after 1s
CICD NeMo / code-linting (push) Has been skipped
Build, validate, and release Neural Modules / release (push) Has been skipped
Build, validate, and release Neural Modules / release-summary (push) Has been cancelled
CICD NeMo / cicd-test-container-build (push) Has been cancelled
CICD NeMo / cicd-import-tests (push) Has been cancelled
CICD NeMo / L0_Setup_Test_Data_And_Models (push) Has been cancelled
CICD NeMo / cicd-main-unit-tests (push) Has been cancelled
CICD NeMo / cicd-main-speech (push) Has been cancelled
CICD NeMo / Nemo_CICD_Test (push) Has been cancelled
CICD NeMo / Coverage (e2e) (push) Has been cancelled
CICD NeMo / Coverage (unit-test) (push) Has been cancelled
CodeQL / Analyze (python) (push) Has been cancelled
CICD NeMo / cicd-wait-in-queue (push) Has been cancelled
123 lines
4.2 KiB
YAML
123 lines
4.2 KiB
YAML
name: "BNR2"
|
|
|
|
model:
|
|
type: bnr
|
|
sample_rate: 16000
|
|
fft_length: 1920
|
|
hop_length: 480
|
|
num_mels: 320
|
|
skip_nan_grad: false
|
|
num_outputs: 1
|
|
segment: 4
|
|
|
|
train: # Parameters related to training
|
|
enable_weight_norm: true
|
|
|
|
optim:
|
|
name: adam
|
|
lr: 0.0005
|
|
sched:
|
|
name: StepLR
|
|
gamma: 0.999
|
|
step_size: 2
|
|
|
|
train_ds:
|
|
manifest_filepath: ???
|
|
input_key: noisy_filepath # key of the input signal path in the manifest
|
|
target_key: speech_filepath # key of the target signal path in the manifest
|
|
target_channel_selector: 0 # target signal is the first channel from files in target_key
|
|
audio_duration: 4.0 # in seconds, audio segment duration for training
|
|
random_offset: true # if the file is longer than audio_duration, use random offset to select a subsegment
|
|
min_duration: ${model.train_ds.audio_duration}
|
|
batch_size: 64 # batch size may be increased based on the available memory
|
|
shuffle: true
|
|
num_workers: 8
|
|
pin_memory: true
|
|
|
|
validation_ds:
|
|
manifest_filepath: ???
|
|
input_key: noisy_filepath # key of the input signal path in the manifest
|
|
target_key: speech_filepath # key of the target signal path in the manifest
|
|
target_channel_selector: 0 # target signal is the first channel from files in target_key
|
|
audio_duration: 10.0 # in seconds, audio segment duration for validation
|
|
min_duration: ${model.validation_ds.audio_duration}
|
|
batch_size: 64 # batch size may be increased based on the available memory
|
|
shuffle: false
|
|
num_workers: 4
|
|
pin_memory: true
|
|
|
|
test_ds:
|
|
manifest_filepath: ???
|
|
input_key: noisy_filepath # key of the input signal path in the manifest
|
|
target_key: speech_filepath # key of the target signal path in the manifest
|
|
target_channel_selector: 0 # target signal is the first channel from files in target_key
|
|
audio_duration: 10.0 # in seconds, audio segment duration for validation
|
|
min_duration: ${model.test_ds.audio_duration}
|
|
batch_size: 1 # batch size may be increased based on the available memory
|
|
shuffle: false
|
|
num_workers: 4
|
|
pin_memory: true
|
|
|
|
loss:
|
|
_target_: nemo.collections.audio.losses.maxine.CombinedLoss
|
|
sample_rate: ${model.sample_rate}
|
|
fft_length: ${model.fft_length}
|
|
hop_length: ${model.hop_length}
|
|
num_mels: ${model.num_mels}
|
|
sisnr_loss_weight: 1
|
|
spectral_loss_weight: 15
|
|
asr_loss_weight: 1
|
|
use_asr_loss: true
|
|
use_mel_spec: true
|
|
|
|
metrics:
|
|
val:
|
|
sdr: # output SDR
|
|
_target_: torchmetrics.audio.SignalDistortionRatio
|
|
test:
|
|
sdr_ch0: # SDR on output channel 0
|
|
_target_: torchmetrics.audio.SignalDistortionRatio
|
|
channel: 0
|
|
|
|
trainer:
|
|
devices: -1 # number of GPUs, -1 would use all available GPUs
|
|
num_nodes: 1
|
|
max_epochs: -1
|
|
max_steps: -1 # computed at runtime if not set
|
|
val_check_interval: 1.0 # Set to 0.25 to check 4 times per epoch, or an int for number of iterations
|
|
accelerator: gpu
|
|
strategy: ddp
|
|
accumulate_grad_batches: 1
|
|
gradient_clip_val: 5
|
|
precision: 32 # Should be set to 16 for O1 and O2 to enable the AMP.
|
|
log_every_n_steps: 25 # Interval of logging.
|
|
enable_progress_bar: true
|
|
num_sanity_val_steps: 0 # number of steps to perform validation steps for sanity check the validation process before starting the training, setting to 0 disables it
|
|
check_val_every_n_epoch: 1 # number of evaluations on validation every n epochs
|
|
sync_batchnorm: true
|
|
enable_checkpointing: False # Provided by exp_manager
|
|
logger: false # Provided by exp_manager
|
|
|
|
exp_manager:
|
|
exp_dir: null
|
|
name: ${name}
|
|
create_tensorboard_logger: true
|
|
create_checkpoint_callback: true
|
|
checkpoint_callback_params:
|
|
# in case of multiple validation sets, first one is used
|
|
monitor: "val_loss"
|
|
mode: "min"
|
|
save_top_k: 5
|
|
always_save_nemo: true # saves the checkpoints as nemo files instead of PTL checkpoints
|
|
|
|
resume_from_checkpoint: null # The path to a checkpoint file to continue the training, restores the whole state including the epoch, step, LR schedulers, apex, etc.
|
|
# you need to set these two to true to continue the training
|
|
resume_if_exists: false
|
|
resume_ignore_no_checkpoint: false
|
|
|
|
# You may use this section to create a W&B logger
|
|
create_wandb_logger: false
|
|
wandb_logger_kwargs:
|
|
name: null
|
|
project: null
|