cleanup

models/ckpt/ar+nar-retnet-4/fp32.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:91781616d713a424cab977abb718888323d1a26461bef78c8065ac30d1258d2a
-size 424338659

models/ckpt/ar-retnet-4/fp32.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e042d05f14f21a166cd5f5c16b9c9c4ac9ce18af2a4c285c7f0d3ef3ea6729bf
-size 418040575

models/ckpt/nar-retnet-4/fp32.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:18027cafe3c077cb8786a5665f04f732f4e3fcacff17844182f9383a1dca640f
-size 422230719

models/config.yaml

@@ -1,104 +0,0 @@
-dataset:
-  training: [
-  ]
-  validation: [
-  ]
-  noise: [
-  ]
-  
-  speaker_name_getter: "lambda p: f'{p.parts[-3]}_{p.parts[-2]}'"
-  
-  use_hdf5: True
-  use_metadata: True
-  hdf5_flag: r
-  validate: True
-
-  workers: 4
-  cache: True
-
-  phones_range: [4, 256]
-  duration_range: [1.0, 16.0]
-
-  random_utterance: 1.0
-  max_prompts: 3
-  prompt_duration: 3.0
-
-  sample_type: speaker
-
-  tasks_list: ["tts"] # , "ns", "sr", "tse", "cse", "nse", "tts"]
-
-models:
-  _prom_levels: 4
-  _max_levels: 4
-
-  _models:
-  - name: "ar"
-    size: "full"
-    resp_levels: 1
-    prom_levels: 2
-    tasks: 8
-    arch_type: "retnet"
-    training: True
-  - name: "nar"
-    size: "full"
-    resp_levels: 3
-    prom_levels: 4
-    tasks: 8
-    arch_type: "retnet"
-    training: True
-
-
-hyperparameters:
-  batch_size: 8
-  gradient_accumulation_steps: 1
-  gradient_clipping: 100
-  
-  optimizer: AdamW
-  learning_rate: 1.0e-5
-  
-  scheduler_type: ""
-
-evaluation:
-  batch_size: 16
-  frequency: 500
-  size: 16
-  
-  steps: 300
-  ar_temperature: 0.95
-  nar_temperature: 0.25
-  load_disabled_engines: True
-
-trainer:
-  iterations: 1_000_000
-  
-  save_tag: step
-  save_on_oom: True
-  save_on_quit: True
-  save_frequency: 100
-  export_on_save: True
-
-  keep_last_checkpoints: 4
-
-  load_state_dict: True
-
-  gc_mode: None # "global_step"
-
-  weight_dtype: bfloat16
-  amp: False
-
-  backend: deepspeed
-  deepspeed:
-    zero_optimization_level: 0
-    use_compression_training: True
-
-  activation_checkpointing: True
-
-inference:
-  use_vocos: True
-  normalize: False
-
-bitsandbytes:
-  enabled: False
-  injects: False
-  linear: False
-  embedding: False