|
sample_rate: 24_000 |
|
audio_backend: "vocos" |
|
|
|
models: |
|
- name: "ar+nar" |
|
size: "full" |
|
resp_levels: 8 |
|
prom_levels: 8 |
|
tasks: 8 |
|
langs: 2 |
|
tones: 1 |
|
arch_type: llama |
|
training: False |
|
version: 5 |
|
attention: auto |
|
dropout: 0.1 |
|
loss_factors: |
|
text: 0.01 |
|
prom: 0.5 |
|
resp: 1.0 |
|
capabilities: ["ar", "nar"] |
|
experimental: |
|
audio_embedding_sums: False |
|
unified_position_ids: False |
|
split_classifiers: True |
|
|
|
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: 8 |
|
gradient_clipping: 1.0 |
|
warmup_steps: 250 |
|
|
|
optimizer: Prodigy |
|
learning_rate: 1.0 |
|
torch_optimizer: True |
|
|
|
scheduler: "" |
|
torch_scheduler: True |
|
|
|
evaluation: |
|
batch_size: 16 |
|
frequency: 1000 |
|
size: 16 |
|
|
|
steps: 500 |
|
ar_temperature: 0.95 |
|
nar_temperature: 0.25 |
|
load_disabled_engines: True |
|
|
|
trainer: |
|
|
|
ddp: False |
|
check_for_oom: False |
|
iterations: 1_000_000 |
|
|
|
save_tag: step |
|
save_on_oom: True |
|
save_on_quit: True |
|
save_frequency: 500 |
|
export_on_save: True |
|
|
|
keep_last_checkpoints: 8 |
|
|
|
aggressive_optimizations: False |
|
load_disabled_engines: False |
|
gradient_checkpointing: True |
|
|
|
|
|
strict_loading: False |
|
|
|
|
|
|
|
|
|
gc_mode: None |
|
|
|
weight_dtype: bfloat16 |
|
amp: True |
|
|
|
backend: deepspeed |
|
deepspeed: |
|
inferencing: True |
|
zero_optimization_level: 0 |
|
use_compression_training: False |
|
|
|
amp: False |
|
|
|
load_webui: False |
|
|
|
inference: |
|
backend: deepspeed |
|
audio_backend: "vocos" |
|
normalize: False |
|
|
|
weight_dtype: bfloat16 |
|
amp: True |
|
|
|
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: 6 |
|
cache: True |
|
|
|
duration_range: [24.0, 32.0] |
|
|
|
random_utterance: 1.0 |
|
max_prompts: 1 |
|
prompt_duration_range: [3.0, 9.0] |
|
|
|
max_resps: 1 |
|
p_resp_append: 0.25 |
|
|
|
sample_type: path |
|
|
|
tasks_list: [ "tts" ] |
|
|
|
training: [] |
|
validation: [] |
|
noise: [] |
|
|