xinference 0.14.4.post1__py3-none-any.whl → 0.15.1__py3-none-any.whl

xinference/thirdparty/fish_speech/fish_speech/configs/base.yaml

@@ -0,0 +1,87 @@
+# Base configuration for training a model
+paths:
+  run_dir: results/${project}
+  ckpt_dir: ${paths.run_dir}/checkpoints
+
+hydra:
+  run:
+    dir: ${paths.run_dir}
+
+# Lightning Trainer
+trainer:
+  _target_: lightning.pytorch.trainer.Trainer
+
+  default_root_dir: ${paths.run_dir}
+  accelerator: gpu
+  num_nodes: 1
+  devices: auto
+  strategy:
+    _target_: lightning.pytorch.strategies.DDPStrategy
+    process_group_backend: nccl  # This should be override when training on windows
+
+  precision: bf16-mixed
+
+  # disable validation by epoch end
+  check_val_every_n_epoch: null
+  val_check_interval: 5000
+  max_steps: 100_000
+
+  # Use torch.backends.cudnn.benchmark to speed up training
+  benchmark: true
+
+# Callbacks
+callbacks:
+  model_checkpoint:
+    _target_: lightning.pytorch.callbacks.ModelCheckpoint
+    dirpath: ${paths.ckpt_dir}
+    filename: "step_{step:09d}"
+    save_last: false # additionally always save an exact copy of the last checkpoint to a file last.ckpt
+    save_top_k: 5 # save 5 latest checkpoints
+    monitor: step # use step to monitor checkpoints
+    mode: max # save the latest checkpoint with the highest global_step
+    every_n_epochs: null # don't save checkpoints by epoch end
+    every_n_train_steps: 5000 # save checkpoints every 5000 steps
+    auto_insert_metric_name: false
+
+  model_summary:
+    _target_: lightning.pytorch.callbacks.ModelSummary
+    max_depth: 2 # the maximum depth of layer nesting that the summary will include
+
+  learning_rate_monitor:
+    _target_: lightning.pytorch.callbacks.LearningRateMonitor
+    logging_interval: step
+    log_momentum: false
+
+  grad_norm_monitor:
+    _target_: fish_speech.callbacks.GradNormMonitor
+    norm_type: 2
+    logging_interval: step
+
+# Logger
+logger:
+  tensorboard:
+    _target_: lightning.pytorch.loggers.tensorboard.TensorBoardLogger
+    save_dir: "${paths.run_dir}/tensorboard/"
+    name: null
+    log_graph: false
+    default_hp_metric: true
+    prefix: ""
+
+  # wandb:
+  #   _target_: lightning.pytorch.loggers.wandb.WandbLogger
+  #   # name: "" # name of the run (normally generated by wandb)
+  #   save_dir: "${paths.run_dir}"
+  #   offline: False
+  #   id: null # pass correct id to resume experiment!
+  #   anonymous: null # enable anonymous logging
+  #   project: "fish-speech"
+  #   log_model: False # upload lightning ckpts
+  #   prefix: "" # a string to put at the beginning of metric keys
+  #   # entity: "" # set to name of your wandb team
+  #   group: ""
+  #   tags: ["vq", "hq", "finetune"]
+  #   job_type: ""
+    
+# Loop
+train: true
+test: false

xinference/thirdparty/fish_speech/fish_speech/configs/firefly_gan_vq.yaml

@@ -0,0 +1,33 @@
+_target_: fish_speech.models.vqgan.modules.firefly.FireflyArchitecture
+spec_transform:
+  _target_: fish_speech.utils.spectrogram.LogMelSpectrogram
+  sample_rate: 44100
+  n_mels: 160
+  n_fft: 2048
+  hop_length: 512
+  win_length: 2048
+backbone:
+  _target_: fish_speech.models.vqgan.modules.firefly.ConvNeXtEncoder
+  input_channels: 160
+  depths: [3, 3, 9, 3]
+  dims: [128, 256, 384, 512]
+  drop_path_rate: 0.2
+  kernel_size: 7
+head:
+  _target_: fish_speech.models.vqgan.modules.firefly.HiFiGANGenerator
+  hop_length: 512
+  upsample_rates: [8, 8, 2, 2, 2]  # aka. strides
+  upsample_kernel_sizes: [16, 16, 4, 4, 4]
+  resblock_kernel_sizes: [3, 7, 11]
+  resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
+  num_mels: 512
+  upsample_initial_channel: 512
+  pre_conv_kernel_size: 13
+  post_conv_kernel_size: 13
+quantizer:
+  _target_: fish_speech.models.vqgan.modules.fsq.DownsampleFiniteScalarQuantize
+  input_dim: 512
+  n_groups: 8
+  n_codebooks: 1
+  levels: [8, 5, 5, 5]
+  downsample_factor: [2, 2]

xinference/thirdparty/fish_speech/fish_speech/configs/lora/r_8_alpha_16.yaml

@@ -0,0 +1,4 @@
+_target_: fish_speech.models.text2semantic.lora.LoraConfig
+r: 8
+lora_alpha: 16
+lora_dropout: 0.01

xinference/thirdparty/fish_speech/fish_speech/configs/text2semantic_finetune.yaml

@@ -0,0 +1,83 @@
+defaults:
+  - base
+  - _self_
+
+project: text2semantic_finetune_dual_ar
+max_length: 4096
+pretrained_ckpt_path: checkpoints/fish-speech-1.4
+
+# Lightning Trainer
+trainer:
+  accumulate_grad_batches: 1
+  gradient_clip_val: 1.0
+  gradient_clip_algorithm: "norm"
+  max_steps: 1000
+  precision: bf16-true
+  limit_val_batches: 10
+  val_check_interval: 100
+
+# Dataset Configuration
+tokenizer:
+  _target_: transformers.AutoTokenizer.from_pretrained
+  pretrained_model_name_or_path: ${pretrained_ckpt_path}
+
+# Dataset Configuration
+train_dataset:
+  _target_: fish_speech.datasets.semantic.AutoTextSemanticInstructionDataset
+  proto_files:
+    - data/protos
+  tokenizer: ${tokenizer}
+  causal: true
+  max_length: ${max_length}
+  use_speaker: false
+  interactive_prob: 0.7
+
+val_dataset:
+  _target_: fish_speech.datasets.semantic.AutoTextSemanticInstructionDataset
+  proto_files:
+    - data/protos
+  tokenizer: ${tokenizer}
+  causal: true
+  max_length: ${max_length}
+  use_speaker: false
+  interactive_prob: 0.7
+
+data:
+  _target_: fish_speech.datasets.semantic.SemanticDataModule
+  train_dataset: ${train_dataset}
+  val_dataset: ${val_dataset}
+  num_workers: 4
+  batch_size: 8
+  tokenizer: ${tokenizer}
+  max_length: ${max_length}
+
+# Model Configuration
+model:
+  _target_: fish_speech.models.text2semantic.lit_module.TextToSemantic
+  model: 
+    _target_: fish_speech.models.text2semantic.llama.BaseTransformer.from_pretrained
+    path: ${pretrained_ckpt_path}
+    load_weights: true
+    max_length: ${max_length}
+    lora_config: null
+
+  optimizer:
+    _target_: torch.optim.AdamW
+    _partial_: true
+    lr: 1e-4
+    weight_decay: 0
+    betas: [0.9, 0.95]
+    eps: 1e-5
+
+  lr_scheduler:
+    _target_: torch.optim.lr_scheduler.LambdaLR
+    _partial_: true
+    lr_lambda:
+      _target_: fish_speech.scheduler.get_constant_schedule_with_warmup_lr_lambda
+      _partial_: true
+      num_warmup_steps: 10
+
+# Callbacks
+callbacks:
+  model_checkpoint:
+    every_n_train_steps: ${trainer.val_check_interval}

xinference/thirdparty/fish_speech/fish_speech/datasets/protos/text-data.proto

@@ -0,0 +1,24 @@
+syntax = "proto3";
+
+package text_data;
+
+message Semantics {
+    repeated uint32 values = 1;
+}
+
+message Sentence {
+    repeated string texts = 1;
+    repeated Semantics semantics = 3;
+}
+
+message TextData {
+    string source = 1;
+    string name = 2;
+    repeated Sentence sentences = 4;
+}
+
+message SampledData {
+    string source = 1;
+    string name = 2;
+    repeated Sentence samples = 3;
+}

xinference/thirdparty/fish_speech/fish_speech/i18n/README.md

@@ -0,0 +1,27 @@
+## i18n Folder Attribution
+
+The `i18n` folder within the `fish_speech` directory contains files initially sourced from the RVC project. In compliance with the MIT license under which these files were released, we acknowledge the original authors and sources below:
+
+### fish_speech/i18n/core.py
+
+**Related code from RVC:**
+[https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/83d6a64e675d9bbd6e92ee450c5f807ed2bb54d8/i18n/i18n.py](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/83d6a64e675d9bbd6e92ee450c5f807ed2bb54d8/i18n/i18n.py)
+
+**Initial commit:**
+add localization(添加本地化) [RVC-Project/Retrieval-based-Voice-Conversion-WebUI#35](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/pull/35)
+
+**Initial author:**
+[@L4Ph](https://github.com/L4Ph)
+
+### fish_speech/i18n/scan.py
+
+**Related code from RVC:**
+[https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/83d6a64e675d9bbd6e92ee450c5f807ed2bb54d8/i18n/scan_i18n.py](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/83d6a64e675d9bbd6e92ee450c5f807ed2bb54d8/i18n/scan_i18n.py)
+
+**Initial commit:**
+File for detecting i18n missing keys [RVC-Project/Retrieval-based-Voice-Conversion-WebUI#1058](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/pull/1058)
+
+**Initial author:**
+[@towzeur](https://github.com/towzeur)
+
+We appreciate the contributions of the RVC project and its authors.

xinference/thirdparty/fish_speech/fish_speech/i18n/locale/en_US.json

@@ -72,7 +72,7 @@
   "Put your text here.": "Put your text here.",
   "Reference Audio": "Reference Audio",
   "Reference Text": "Reference Text",
-  "Related code are released under BSD-3-Clause License, and weights are released under CC BY-NC-SA 4.0 License.": "Related code are released under BSD-3-Clause License, and weights are released under CC BY-NC-SA 4.0 License.",
+  "Related code and weights are released under CC BY-NC-SA 4.0 License.": "Related code and weights are released under CC BY-NC-SA 4.0 License.",
   "Remove Selected Data": "Remove Selected Data",
   "Removed path successfully!": "Removed path successfully!",
   "Repetition Penalty": "Repetition Penalty",

xinference/thirdparty/fish_speech/fish_speech/i18n/locale/es_ES.json

@@ -72,7 +72,7 @@
   "Put your text here.": "Ponga su texto aquí.",
   "Reference Audio": "Audio de Referencia",
   "Reference Text": "Texto de Referencia",
-  "Related code are released under BSD-3-Clause License, and weights are released under CC BY-NC-SA 4.0 License.": "El código relacionado se publica bajo la Licencia BSD-3-Clause, y los pesos se publican bajo la Licencia CC BY-NC-SA 4.0.",
+  "Related code and weights are released under CC BY-NC-SA 4.0 License.": "El código relacionado y los pesos se publican bajo la Licencia CC BY-NC-SA 4.0.",
   "Remove Selected Data": "Eliminar Datos Seleccionados",
   "Removed path successfully!": "¡Ruta eliminada exitosamente!",
   "Repetition Penalty": "Penalización por Repetición",

xinference/thirdparty/fish_speech/fish_speech/i18n/locale/ja_JP.json

@@ -72,7 +72,7 @@
   "Put your text here.": "ここにテキストを入力してください。",
   "Reference Audio": "リファレンスオーディオ",
   "Reference Text": "リファレンステキスト",
-  "Related code are released under BSD-3-Clause License, and weights are released under CC BY-NC-SA 4.0 License.": "関連コードはBSD-3-Clauseライセンスの下でリリースされ、重みはCC BY-NC-SA 4.0ライセンスの下でリリースされます。",
+  "Related code and weights are released under CC BY-NC-SA 4.0 License.": "関連コードと重みはCC BY-NC-SA 4.0ライセンスの下でリリースされます。",
   "Remove Selected Data": "選択したデータを削除",
   "Removed path successfully!": "パスの削除に成功しました！",
   "Repetition Penalty": "反復ペナルティ",

xinference/thirdparty/fish_speech/fish_speech/i18n/locale/pt_BR.json

@@ -84,7 +84,7 @@
   "Reference Text": "Texto de Referência",
   "warning": "Aviso",
   "Pre-processing begins...": "O pré-processamento começou!",
-  "Related code are released under BSD-3-Clause License, and weights are released under CC BY-NC-SA 4.0 License.": "O código relacionado é licenciado sob a Licença BSD-3-Clause, e os pesos sob a Licença CC BY-NC-SA 4.0.",
+  "Related code and weights are released under CC BY-NC-SA 4.0 License.": "O código relacionado e os pesos são licenciados sob a Licença CC BY-NC-SA 4.0.",
   "Remove Selected Data": "Remover Dados Selecionados",
   "Removed path successfully!": "Caminho removido com sucesso!",
   "Repetition Penalty": "Penalidade de Repetição",

xinference/thirdparty/fish_speech/fish_speech/i18n/locale/zh_CN.json

@@ -72,7 +72,7 @@
   "Put your text here.": "在此处输入文本.",
   "Reference Audio": "参考音频",
   "Reference Text": "参考文本",
-  "Related code are released under BSD-3-Clause License, and weights are released under CC BY-NC-SA 4.0 License.": "相关代码使用 BSD-3-Clause 许可证发布，权重使用 CC BY-NC-SA 4.0 许可证发布.",
+  "Related code and weights are released under CC BY-NC-SA 4.0 License.": "相关代码和权重使用 CC BY-NC-SA 4.0 许可证发布.",
   "Remove Selected Data": "移除选中数据",
   "Removed path successfully!": "移除路径成功!",
   "Repetition Penalty": "重复惩罚",

xinference/thirdparty/fish_speech/fish_speech/models/text2semantic/llama.py

@@ -353,7 +353,7 @@ class BaseTransformer(nn.Module):
 
             if "int8" in str(Path(path)):
                 logger.info("Using int8 weight-only quantization!")
-                from ...tools.llama.quantize import WeightOnlyInt8QuantHandler
+                from tools.llama.quantize import WeightOnlyInt8QuantHandler
 
                 simple_quantizer = WeightOnlyInt8QuantHandler(model)
                 model = simple_quantizer.convert_for_runtime()
@@ -363,7 +363,7 @@ class BaseTransformer(nn.Module):
                 path_comps = path.name.split("-")
                 assert path_comps[-2].startswith("g")
                 groupsize = int(path_comps[-2][1:])
-                from ...tools.llama.quantize import WeightOnlyInt4QuantHandler
+                from tools.llama.quantize import WeightOnlyInt4QuantHandler
 
                 simple_quantizer = WeightOnlyInt4QuantHandler(model, groupsize)
                 model = simple_quantizer.convert_for_runtime()

xinference/thirdparty/fish_speech/fish_speech/models/vqgan/__init__.py

@@ -1,3 +0,0 @@
-from .lit_module import VQGAN
-
-__all__ = ["VQGAN"]