vall-e/data/config.yaml

147 lines
2.5 KiB
YAML
Executable File

models:
- name: "ar+nar"
size: "full"
resp_levels: 8
prom_levels: 8
tasks: 8
langs: 2
tones: 1
arch_type: "retnet"
training: True
version: 3
hyperparameters:
batch_size: 4
gradient_accumulation_steps: 4
gradient_clipping: 10
optimizer: Adagrad
torch_optimizer: True
learning_rate: 1.0e-2
scheduler_type: ""
#scheduler_type: OneCycle
#scheduler_params:
# cycle_first_step_size: 10_000
# cycle_first_stair_count: 10_000
# cycle_second_step_size: 15_000
# cycle_second_stair_count: 15_000
# decay_step_size: 5_000
# cycle_min_lr: 2.5e-4 # 1.0e-5
# cycle_max_lr: 2.5e-4 # 1.0e-4
# decay_lr_rate: 0.0
# cycle_min_mom: 0.90
# cycle_max_mom: 0.99
# decay_mom_rate: 0.0
evaluation:
batch_size: 8
frequency: 10000
size: 8
steps: 500
ar_temperature: 0.95
nar_temperature: 0.25
load_disabled_engines: True
trainer:
no_logger: True
iterations: 1_000_000
save_tag: step
save_on_oom: True
save_on_quit: True
save_frequency: 250
export_on_save: True
keep_last_checkpoints: 4
aggressive_optimizations: False
load_disabled_engines: False
#load_state_dict: True
strict_loading: False
#load_tag: "9500"
#load_states: False
#restart_step_count: True
gc_mode: None # "global_step"
weight_dtype: float32
amp: False
backend: deepspeed
deepspeed:
inferencing: True
zero_optimization_level: 0
use_compression_training: False
activation_checkpointing: True
load_webui: True
inference:
backend: deepspeed
audio_backend: "dac"
normalize: False
weight_dtype: float32
amp: False
bitsandbytes:
enabled: False
injects: False
replace: False
linear: False
embedding: False
bitnet: False
fp8:
enabled: False
backend: "te"
experimental: True
dataset:
speaker_name_getter: "lambda p: f'{p.parts[-3]}_{p.parts[-2]}'"
speaker_group_getter: "lambda p: f'{p.parts[-3]}'"
speaker_languages:
ja: []
use_hdf5: True
use_metadata: True
hdf5_flag: r
validate: True
workers: 8
cache: True
#phones_range: [4, 512]
#duration_range: [1.0, 32.0]
phones_range: [0, 512]
duration_range: [0.0, 64.0]
random_utterance: 1.0
max_prompts: 3
prompt_duration: 6.0
max_resps: 1
p_resp_append: 0.25
sample_type: speaker
tasks_list: [ "tts" ] # , [ "tts", "tts-c", "ns", "sr", "tse", "cse", "nse", "tts"]
training: []
validation: []
noise: []