140 lines
2.4 KiB
YAML
140 lines
2.4 KiB
YAML
experimental: False # should probably expand this into a dict of experimental flags
|
|
sample_rate: 24_000 # 44_000 for dac
|
|
audio_backend: "vocos" # or dac
|
|
|
|
models:
|
|
- name: "ar+nar"
|
|
size: "full"
|
|
resp_levels: 8
|
|
prom_levels: 8
|
|
tasks: 8
|
|
langs: 2
|
|
tones: 1
|
|
arch_type: llama
|
|
training: True
|
|
version: 5
|
|
attention: flash_attention_2
|
|
dropout: 0.1
|
|
experimental: False
|
|
|
|
loss_factors:
|
|
text: 0.1
|
|
prom: 0.0
|
|
resp: 1.0
|
|
|
|
hyperparameters:
|
|
autotune: False
|
|
autotune_params:
|
|
start_profile_step: 1
|
|
end_profile_step: 50
|
|
num_tuning_micro_batch_sizes: 8
|
|
|
|
batch_size: 16
|
|
gradient_accumulation_steps: 4
|
|
gradient_clipping: 1.0
|
|
warmup_steps: 100
|
|
|
|
optimizer: Prodigy
|
|
learning_rate: 1.0
|
|
torch_optimizer: True
|
|
|
|
scheduler: "" # ScheduleFree
|
|
torch_scheduler: True
|
|
|
|
evaluation:
|
|
batch_size: 8
|
|
frequency: 5000
|
|
size: 8
|
|
|
|
steps: 500
|
|
ar_temperature: 0.95
|
|
nar_temperature: 0.25
|
|
load_disabled_engines: True
|
|
|
|
trainer:
|
|
#no_logger: True
|
|
ddp: False
|
|
#check_for_oom: False
|
|
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
|
|
|
|
gradient_checkpointing: True
|
|
|
|
strict_loading: False
|
|
#load_state_dict: True
|
|
#load_tag: "9500"
|
|
#load_states: False
|
|
#restart_step_count: True
|
|
|
|
gc_mode: None # "global_step"
|
|
|
|
weight_dtype: float32 # float16 or bfloat16
|
|
amp: False
|
|
|
|
backend: deepspeed
|
|
deepspeed:
|
|
inferencing: True
|
|
zero_optimization_level: 0
|
|
use_compression_training: False
|
|
|
|
amp: False
|
|
|
|
load_webui: False
|
|
|
|
inference:
|
|
backend: deepspeed
|
|
normalize: False
|
|
|
|
weight_dtype: float32 # float16 or bfloat16
|
|
amp: False
|
|
|
|
optimizations:
|
|
injects: False
|
|
replace: True
|
|
|
|
linear: False
|
|
embedding: False
|
|
optimizers: True
|
|
|
|
bitsandbytes: False
|
|
dadaptation: False
|
|
bitnet: False
|
|
fp8: False
|
|
|
|
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: 2
|
|
cache: True
|
|
|
|
duration_range: [3.0, 5.0]
|
|
|
|
random_utterance: 1.0
|
|
max_prompts: 1
|
|
prompt_duration: 3.0
|
|
|
|
max_resps: 1
|
|
p_resp_append: 0.25
|
|
|
|
sample_type: path # speaker
|
|
|
|
tasks_list: [ "tts" ] # , [ "tts", "tts-c", "ns", "sr", "tse", "cse", "nse", "tts"]
|
|
|
|
training: []
|
|
validation: []
|
|
noise: [] |