xinference 0.14.4.post1__py3-none-any.whl → 0.15.0__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 +1,34 @@
+_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
+  use_template: false
+  pre_conv_kernel_size: 13
+  post_conv_kernel_size: 13
+quantizer:
+  _target_: fish_speech.models.vqgan.modules.fsq.DownsampleFiniteScalarQuantize
+  input_dim: 512
+  n_groups: 4
+  n_codebooks: 1
+  levels: [8, 5, 5, 5]
+  downsample_factor: [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-1.2-sft
+
+# 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/text/chn_text_norm/.gitignore

@@ -0,0 +1,114 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+
+# JetBrains PyCharm
+.idea
+
+# Customize
+references
+url.txt
+
+# Git
+.git

xinference/thirdparty/fish_speech/fish_speech/text/chn_text_norm/README.md

@@ -0,0 +1,36 @@
+# This account is no longer in use, see [Atomicoo](https://github.com/atomicoo) for my latest works.
+
+# Chn Text Norm
+
+this is a repository for chinese text normalization (no longer maintained).
+
+## Quick Start ##
+
+### Git Clone Repo ###
+
+git clone this repo to the root directory of your project which need to use it.
+
+    cd /path/to/proj
+    git clone https://github.com/Joee1995/chn-text-norm.git
+
+after that, your doc tree should be:
+```
+proj                     # root of your project
+|--- chn_text_norm       # this chn-text-norm tool
+     |--- text.py
+     |--- ...
+|--- text_normalize.py   # your text normalization code
+|--- ...
+```
+
+### How to Use ? ###
+
+    # text_normalize.py
+    from chn_text_norm.text import *
+    
+    raw_text = 'your raw text'
+    text = Text(raw_text=raw_text).normalize()
+
+### How to add quantums ###
+
+打开test.py，然后你就知道怎么做了。

xinference/thirdparty/fish_speech/fish_speech/webui/css/style.css

@@ -0,0 +1,161 @@
+:root {
+  --my-200: #80eeee;
+  --my-50: #ecfdf5;
+  --water-width: 300px;
+  --water-heigh: 300px;
+}
+
+
+/* general styled components */
+.tools {
+  align-items: center;
+  justify-content: center;
+}
+
+.gradio-button {
+    max-width: 2.2em;
+    min-width: 2.2em !important;
+    height: 2.4em;
+    align-self: end;
+    line-height: 1em;
+    border-radius: 0.5em;
+
+}
+
+.gradio-button.secondary-down, .gradio-button.secondary-down:hover{
+    box-shadow: 1px 1px 1px rgba(0,0,0,0.25) inset, 0px 0px 3px rgba(0,0,0,0.15) inset;
+}
+
+/* replace original footer with ours */
+a{
+    font-weight: bold;
+    cursor: pointer;
+    color: #030C14 !important;
+}
+
+footer {
+    display: none !important;
+}
+
+#footer{
+    text-align: center;
+}
+
+#footer div{
+    display: inline-block;
+}
+
+#footer .versions{
+    font-size: 85%;
+    opacity: 0.85;
+}
+
+/*@keyframes moveBackground {*/
+/*  0% {*/
+/*    background-position: 0 0;*/
+/*  }*/
+/*  100% {*/
+/*    background-position: -100px 100px;*/
+/*  }*/
+/*}*/
+@keyframes moveJellyBackground {
+  0% {
+    background-position: 0% 50%;
+  }
+  50% {
+    background-position: 100% 50%;
+  }
+  100% {
+    background-position: 0% 50%;
+  }
+}
+
+.gradio-container {
+  position: absolute;
+  z-index: 10;
+}
+
+
+.quan {
+  position: absolute;
+  bottom: 0;
+  width: var(--water-width);
+  height: var(--water-heigh);
+  border-radius: 0;
+  /*border: 3px solid rgb(246, 247, 248);*/
+  /*box-shadow: 0 0 0 3px rgb(41, 134, 196);*/
+  z-index: 0;
+
+}
+
+.quan:last-child {
+  margin-right: 0;
+}
+
+.shui {
+  position: absolute;
+  top: 0;
+  left: 0;
+  width: 100%;
+  height: 100%;
+  background-color: rgb(23, 106, 201);
+  border-radius: 0;
+  overflow: hidden;
+  z-index: 0;
+}
+
+.shui::after {
+
+  content: '';
+  position: absolute;
+  top: 20%;
+  left: 50%;
+  width: 150%;
+  height: 150%;
+  border-radius: 40%;
+  background-image: radial-gradient(circle at 0% 50%, #dcfcf1, var(--my-50) 50%);
+  animation: shi 5s linear infinite;
+}
+
+@keyframes shi {
+  0% {
+    transform: translate(-50%, -65%) rotate(0deg);
+  }
+  100% {
+    transform: translate(-50%, -65%) rotate(360deg);
+  }
+}
+
+.shui::before {
+  content: '';
+  position: absolute;
+  top: 20%;
+  left: 50%;
+  width: 150%;
+  height: 150%;
+  border-radius: 42%;
+  background-color: rgb(240, 228, 228, 0.2);
+  animation: xu 7s linear infinite;
+}
+
+@keyframes xu {
+  0% {
+    transform: translate(-50%, -60%) rotate(0deg);
+  }
+  100% {
+    transform: translate(-50%, -60%) rotate(360deg);
+  }
+}
+
+fieldset.data_src div.wrap label {
+  background: #f8bffee0 !important;
+}
+
+.scrollable-component {
+  max-height: 100px;
+  overflow-y: auto;
+}
+
+#file_accordion {
+  max-height: 220px !important;
+}

xinference/thirdparty/fish_speech/fish_speech/webui/html/footer.html

@@ -0,0 +1,11 @@
+<div style="color: rgba(25,255,205,0.7) !important;">
+        <a href="{api_docs}">API</a>
+         • 
+        <a href="https://github.com/fishaudio/fish-speech">Github</a>
+         • 
+        <a href="https://gradio.app">Gradio</a>
+</div>
+<br />
+<div class="versions" style="color: rgba(25,255,205,0.7) !important;">
+{versions}
+</div>

xinference/thirdparty/fish_speech/fish_speech/webui/js/animate.js

@@ -0,0 +1,69 @@
+
+function createGradioAnimation() {
+    const params = new URLSearchParams(window.location.search);
+    if (!params.has('__theme')) {
+        params.set('__theme', 'light');
+        window.location.search = params.toString();
+    }
+
+    var gradioApp = document.querySelector('gradio-app');
+    if (gradioApp) {
+
+        document.documentElement.style.setProperty('--my-200', '#80eeee');
+        document.documentElement.style.setProperty('--my-50', '#ecfdf5');
+
+        // gradioApp.style.position = 'relative';
+        // gradioApp.style.backgroundSize = '200% 200%';
+        // gradioApp.style.animation = 'moveJellyBackground 10s ease infinite';
+        // gradioApp.style.backgroundImage = 'radial-gradient(circle at 0% 50%, var(--my-200), var(--my-50) 50%)';
+        // gradioApp.style.display = 'flex';
+        // gradioApp.style.justifyContent = 'flex-start';
+        // gradioApp.style.flexWrap = 'nowrap';
+        // gradioApp.style.overflowX = 'auto';
+
+        // for (let i = 0; i < 6; i++) {
+        //     var quan = document.createElement('div');
+        //     quan.className = 'quan';
+        //     gradioApp.insertBefore(quan, gradioApp.firstChild);
+        //     quan.id = 'quan' + i.toString();
+        //     quan.style.left = 'calc(var(--water-width) * ' + i.toString() + ')';
+        //     var quanContainer = document.querySelector('.quan');
+        //     if (quanContainer) {
+        //         var shui = document.createElement('div');
+        //         shui.className = 'shui';
+        //         quanContainer.insertBefore(shui, quanContainer.firstChild)
+        //     }
+        // }
+    }
+
+    var container = document.createElement('div');
+    container.id = 'gradio-animation';
+    container.style.fontSize = '2em';
+    container.style.fontFamily = 'Maiandra GD, ui-monospace, monospace';
+    container.style.fontWeight = 'bold';
+    container.style.textAlign = 'center';
+    container.style.marginBottom = '20px';
+
+    var text = 'Welcome to Fish-Speech!';
+    for (var i = 0; i < text.length; i++) {
+        (function(i){
+            setTimeout(function(){
+                var letter = document.createElement('span');
+                letter.style.opacity = '0';
+                letter.style.transition = 'opacity 0.5s';
+                letter.innerText = text[i];
+
+                container.appendChild(letter);
+
+                setTimeout(function() {
+                    letter.style.opacity = '1';
+                }, 50);
+            }, i * 200);
+        })(i);
+    }
+
+    var gradioContainer = document.querySelector('.gradio-container');
+    gradioContainer.insertBefore(container, gradioContainer.firstChild);
+
+    return 'Animation created';
+}