models/experiments/config.dac-nar-len.yaml

sample_rate: 44_000
audio_backend: "dac"

models:
- name: "nar-len"
  size:
    audio_tokens: 1024
    text_tokens: 256
    dim: 1024
    heads: 16
    layers: 16
  resp_levels: 9
  prom_levels: 9
  tasks: 8
  langs: 2
  tones: 1
  arch_type: llama
  training: True
  version: 5
  attention: flash_attention_2
  dropout: 0.1
  #loss_factors:
  #  text: 0.01
  #  prom: 0.5
  #  resp: 1.0
  #  len: 1.0
  capabilities: ["nar", "len"]
  experimental:
    audio_embedding_sums: False
    interleave: False
    unified_position_ids: True
    rvq_level_range: []
    split_classifiers: True
    tie_classifier_to_embedding: False

#loras:
#- name : "lora-test"
#  rank: 128
#  alpha: 128
#  training: True
#  rvq_levels: []

hyperparameters:
  batch_size: 16
  gradient_accumulation_steps: 4
  gradient_clipping: 1.0
  warmup_steps: 10

  optimizer: Prodigy
  learning_rate: 1.0
  torch_optimizer: True
  
  scheduler: "" # ScheduleFree
  torch_scheduler: True

evaluation:
  batch_size: 4
  frequency: 250
  size: 4
  
  steps: 500
  ar_temperature: 1.0
  nar_temperature: 0.0

trainer:
  iterations: 1_000_000  
  save_frequency: 250
  keep_last_checkpoints: 4
  
  check_for_oom: False
  gradient_checkpointing: False

  weight_dtype: bfloat16
  amp: False

  backend: deepspeed
  deepspeed:
    inferencing: False
    amp: False

  load_webui: False

inference:
  backend: local
  normalize: False

  weight_dtype: 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]}'"

  use_hdf5: True
  hdf5_flag: r
  
  use_metadata: True
  validate: True

  workers: 1
  cache: False

  duration_range: [3.0, 24.0]

  random_utterance: 1.0
  max_prompts: 1
  prompt_duration_range: [3.0, 3.0]
  
  max_resps: 1
  p_resp_append: 0.25

  sample_type: path # path # speaker
  sample_order: duration
  sample_max_duration_batch: 100

  tasks_list: [ "tts" ] #, "tts-c", "ns", "sr" ]

  training: []
  validation: []
  noise: []