xinference 0.14.1.post1__py3-none-any.whl → 0.14.3__py3-none-any.whl

xinference/thirdparty/fish_speech/tools/extract_model.py

@@ -0,0 +1,21 @@
+import click
+import torch
+from loguru import logger
+
+
+@click.command()
+@click.argument("model_path")
+@click.argument("output_path")
+def main(model_path, output_path):
+    if model_path == output_path:
+        logger.error("Model path and output path are the same")
+        return
+
+    logger.info(f"Loading model from {model_path}")
+    state_dict = torch.load(model_path, map_location="cpu")["state_dict"]
+    torch.save(state_dict, output_path)
+    logger.info(f"Model saved to {output_path}")
+
+
+if __name__ == "__main__":
+    main()

xinference/thirdparty/fish_speech/tools/file.py

@@ -0,0 +1,108 @@
+from pathlib import Path
+from typing import Union
+
+from loguru import logger
+from natsort import natsorted
+
+AUDIO_EXTENSIONS = {
+    ".mp3",
+    ".wav",
+    ".flac",
+    ".ogg",
+    ".m4a",
+    ".wma",
+    ".aac",
+    ".aiff",
+    ".aif",
+    ".aifc",
+}
+
+VIDEO_EXTENSIONS = {
+    ".mp4",
+    ".avi",
+}
+
+
+def list_files(
+    path: Union[Path, str],
+    extensions: set[str] = None,
+    recursive: bool = False,
+    sort: bool = True,
+) -> list[Path]:
+    """List files in a directory.
+
+    Args:
+        path (Path): Path to the directory.
+        extensions (set, optional): Extensions to filter. Defaults to None.
+        recursive (bool, optional): Whether to search recursively. Defaults to False.
+        sort (bool, optional): Whether to sort the files. Defaults to True.
+
+    Returns:
+        list: List of files.
+    """
+
+    if isinstance(path, str):
+        path = Path(path)
+
+    if not path.exists():
+        raise FileNotFoundError(f"Directory {path} does not exist.")
+
+    files = [file for ext in extensions for file in path.rglob(f"*{ext}")]
+
+    if sort:
+        files = natsorted(files)
+
+    return files
+
+
+def load_filelist(path: Path | str) -> list[tuple[Path, str, str, str]]:
+    """
+    Load a Bert-VITS2 style filelist.
+    """
+
+    files = set()
+    results = []
+    count_duplicated, count_not_found = 0, 0
+
+    LANGUAGE_TO_LANGUAGES = {
+        "zh": ["zh", "en"],
+        "jp": ["jp", "en"],
+        "en": ["en"],
+    }
+
+    with open(path, "r", encoding="utf-8") as f:
+        for line in f.readlines():
+            splits = line.strip().split("|", maxsplit=3)
+            if len(splits) != 4:
+                logger.warning(f"Invalid line: {line}")
+                continue
+
+            filename, speaker, language, text = splits
+            file = Path(filename)
+            language = language.strip().lower()
+
+            if language == "ja":
+                language = "jp"
+
+            assert language in ["zh", "jp", "en"], f"Invalid language {language}"
+            languages = LANGUAGE_TO_LANGUAGES[language]
+
+            if file in files:
+                logger.warning(f"Duplicated file: {file}")
+                count_duplicated += 1
+                continue
+
+            if not file.exists():
+                logger.warning(f"File not found: {file}")
+                count_not_found += 1
+                continue
+
+            results.append((file, speaker, languages, text))
+
+    if count_duplicated > 0:
+        logger.warning(f"Total duplicated files: {count_duplicated}")
+
+    if count_not_found > 0:
+        logger.warning(f"Total files not found: {count_not_found}")
+
+    return results

xinference/thirdparty/fish_speech/tools/gen_ref.py

@@ -0,0 +1,36 @@
+import json
+from pathlib import Path
+
+
+def scan_folder(base_path):
+    wav_lab_pairs = {}
+
+    base = Path(base_path)
+    for suf in ["wav", "lab"]:
+        for f in base.rglob(f"*.{suf}"):
+            relative_path = f.relative_to(base)
+            parts = relative_path.parts
+            print(parts)
+            if len(parts) >= 3:
+                character = parts[0]
+                emotion = parts[1]
+
+                if character not in wav_lab_pairs:
+                    wav_lab_pairs[character] = {}
+                if emotion not in wav_lab_pairs[character]:
+                    wav_lab_pairs[character][emotion] = []
+                wav_lab_pairs[character][emotion].append(str(f.name))
+
+    return wav_lab_pairs
+
+
+def save_to_json(data, output_file):
+    with open(output_file, "w", encoding="utf-8") as file:
+        json.dump(data, file, ensure_ascii=False, indent=2)
+
+
+base_path = "ref_data"
+out_ref_file = "ref_data.json"
+
+wav_lab_pairs = scan_folder(base_path)
+save_to_json(wav_lab_pairs, out_ref_file)

xinference/thirdparty/fish_speech/tools/llama/build_dataset.py

@@ -0,0 +1,169 @@
+import itertools
+import os
+import re
+from collections import defaultdict
+from functools import partial
+from multiprocessing import Pool
+from pathlib import Path
+
+import click
+import numpy as np
+from loguru import logger
+from tqdm import tqdm
+
+from fish_speech.datasets.protos.text_data_pb2 import Semantics, Sentence, TextData
+from fish_speech.datasets.protos.text_data_stream import pack_pb_stream
+from fish_speech.utils.file import load_filelist
+
+# To avoid CPU overload
+os.environ["MKL_NUM_THREADS"] = "1"
+os.environ["OMP_NUM_THREADS"] = "1"
+
+
+def task_generator_folder(root: Path, text_extension: str):
+    files = list(tqdm(Path(root).rglob("*.npy"), desc=f"Loading {root}"))
+    files = sorted(files)
+
+    grouped_files = defaultdict(list)
+    for file in tqdm(files, desc=f"Grouping {root}"):
+        p = str(file.parent)
+        speaker = file.parent.name
+
+        try:
+            if isinstance(text_extension, str):
+                texts = [file.with_suffix(text_extension).read_text(encoding="utf-8")]
+            else:
+                texts = [
+                    file.with_suffix(ext).read_text(encoding="utf-8")
+                    for ext in text_extension
+                ]
+        except Exception as e:
+            logger.error(f"Failed to read text {file}: {e}")
+            continue
+
+        grouped_files[p].append((speaker, file, texts))
+
+    logger.info(
+        f"Found {len(grouped_files)} groups in {root}, {list(grouped_files.keys())[:5]}..."
+    )
+
+    for i in grouped_files.values():
+        subset = [(f, t) for _, f, t in i]
+        yield i[0][0], subset, "folder"
+
+
+def task_generator_filelist(filelist):
+    grouped_files = defaultdict(list)
+    for filename, speaker, _, text in load_filelist(filelist):
+        grouped_files[speaker].append((Path(filename), [text]))
+
+    logger.info(f"Found {len(grouped_files)} groups in {filelist}")
+    for speaker, values in grouped_files.items():
+        yield speaker, values, "filelist"
+
+
+def run_task(task):
+    name, subset, source = task
+
+    # Parse the files
+    sentences = []
+    for file, texts in subset:
+        np_file = file.with_suffix(".npy")
+        if np_file.exists() is False:
+            logger.warning(f"Can't find {np_file}")
+            continue
+
+        new_texts = []
+
+        for text in texts:
+            # Simple cleaning: replace { xxx } and < xxx > with space
+            text = re.sub(r"\{.*?\}", " ", text)
+            text = re.sub(r"<.*?>", " ", text)
+            text = re.sub(r"\s+", " ", text)
+            new_texts.append(text)
+
+        try:
+            semantics = np.load(np_file)
+        except Exception as e:
+            logger.error(f"Failed to parse {file}: {e}")
+            continue
+
+        if isinstance(semantics, np.ndarray):
+            semantics = semantics.tolist()
+
+        sentences.append(
+            Sentence(
+                texts=new_texts,
+                semantics=[Semantics(values=s) for s in semantics],
+            )
+        )
+
+    # Pack the sentences
+    return pack_pb_stream(
+        TextData(
+            source=source,
+            name=name,
+            sentences=sentences,
+        )
+    )
+
+
+@click.command()
+@click.option(
+    "--input",
+    type=click.Path(path_type=Path),
+    required=True,
+    help="A folder containing the dataset or a filelist",
+    multiple=True,
+)
+@click.option(
+    "--output", type=click.Path(path_type=Path), default="data/quantized-dataset-ft"
+)
+@click.option("--num-workers", type=int, default=16)
+@click.option("--text-extension", type=str, default=[".txt"], multiple=True)
+@click.option(
+    "--shard-size", type=int, default=10, help="The maximum size of each shard in mb"
+)
+def main(input, output, num_workers, text_extension, shard_size):
+    generator_fns = []
+
+    for f in input:
+        assert f.exists(), f"{f} not found"
+
+        if f.is_dir():
+            generator_fn = task_generator_folder(f, text_extension)
+        else:
+            generator_fn = task_generator_filelist(f)
+
+        generator_fns.append(generator_fn)
+
+    generator_fn = itertools.chain(*generator_fns)
+    output.mkdir(parents=True, exist_ok=True)
+
+    dataset_fp = None
+    tar_idx = 0
+    written_size = 0
+
+    with Pool(num_workers) as p:
+        for result in tqdm(p.imap_unordered(run_task, generator_fn)):
+            if dataset_fp is None:
+                dataset_fp = open(Path(output) / f"{tar_idx:08d}.protos", "wb")
+
+            dataset_fp.write(result)
+            written_size += len(result)
+
+            if written_size > shard_size * 1024 * 1024:
+                logger.info(f"Finished writing {tar_idx} shards to {output}")
+                dataset_fp.close()
+                dataset_fp = None
+                written_size = 0
+                tar_idx += 1
+
+    if dataset_fp is not None:
+        dataset_fp.close()
+
+    logger.info(f"Finished writing {tar_idx + 1} shards to {output}")
+
+
+if __name__ == "__main__":
+    main()

xinference/thirdparty/fish_speech/tools/llama/eval_in_context.py

@@ -0,0 +1,171 @@
+# import pyrootutils
+import torch
+import torch.nn.functional as F
+from matplotlib import pyplot as plt
+from transformers import AutoTokenizer
+
+# register eval resolver and root
+# pyrootutils.setup_root(__file__, indicator=".project-root", pythonpath=True)
+
+from torch.utils.data import DataLoader
+
+from fish_speech.datasets.semantic import AutoAugTextDataset, TextDataCollator
+from tools.llama.generate import load_model
+
+
+def smooth(
+    scalars: list[float], weight: float
+) -> list[float]:  # Weight between 0 and 1
+    last = scalars[0]  # First value in the plot (first timestep)
+    smoothed = list()
+    for point in scalars:
+        smoothed_val = last * weight + (1 - weight) * point  # Calculate smoothed value
+        smoothed.append(smoothed_val)  # Save it
+        last = smoothed_val  # Anchor the last smoothed value
+
+    return smoothed
+
+
+@torch.inference_mode()
+def analyze_one_model(loader, config, weight, max_length):
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+    model = load_model(
+        config,
+        weight,
+        device,
+        torch.bfloat16,
+        max_length,
+        compile=False,
+    )[0]
+
+    current_step = 0
+    model.eval()
+
+    semantic_loss_sum = torch.zeros(
+        max_length,
+        dtype=torch.float32,
+        device=device,
+    )
+    counter = torch.zeros(
+        max_length,
+        dtype=torch.long,
+        device=device,
+    )
+
+    for batch in loader:
+        batch = {k: v.to(device) for k, v in batch.items()}
+
+        labels = batch["labels"]
+        outputs = model(
+            inp=batch["inputs"],
+            key_padding_mask=batch["attention_masks"],
+        )
+
+        token_logits = outputs.token_logits
+        codebook_logits = outputs.codebook_logits
+
+        # Generate labels
+        base_loss = F.cross_entropy(
+            token_logits.reshape(-1, token_logits.size(-1)),
+            labels[:, 0].reshape(-1),
+            ignore_index=-100,
+            reduction="none",
+        )
+
+        codebook_labels = labels[:, 1 : 1 + model.config.num_codebooks].mT
+        semantic_loss = F.cross_entropy(
+            codebook_logits.reshape(-1, codebook_logits.size(-1)),
+            codebook_labels.reshape(-1),
+            ignore_index=-100,
+            reduction="none",
+        )
+
+        base_loss = base_loss.reshape(labels[:, 0].shape)
+        semantic_loss = semantic_loss.reshape(codebook_labels.shape)
+
+        semantic_loss_frame = semantic_loss.mean(-1)
+        pad_pos = codebook_labels.sum(-1) == -100 * model.config.num_codebooks
+
+        for loss_sample, pad in zip(semantic_loss_frame, pad_pos):
+            semantic_loss_sum[~pad] += loss_sample[~pad]
+            counter[~pad] += 1
+
+        current_step += 1
+        if current_step == 10:
+            break
+
+    semantic_loss = semantic_loss.cpu()
+    counter = counter.cpu()
+    xs, ys = [], []
+
+    for i, (loss, count) in enumerate(zip(semantic_loss_sum, counter)):
+        if count > 0:
+            xs.append(i)
+            ys.append((loss / count).item())  # for better loss visualization
+
+    smoothed_ys = smooth(ys, 0.95)
+
+    # Unload model
+    del model
+    torch.cuda.empty_cache()
+
+    return xs, ys, smoothed_ys
+
+
+def main():
+    tokenizer = AutoTokenizer.from_pretrained("fishaudio/fish-speech-1")
+    max_length = 4096
+
+    ds = AutoAugTextDataset(
+        ["data/protos/sft/云天河"],
+        tokenizer=tokenizer,
+        use_speaker=False,
+        interactive_prob=1.0,
+        max_length=max_length,
+    )
+
+    loader = DataLoader(
+        ds,
+        batch_size=8,
+        collate_fn=TextDataCollator(tokenizer, max_length=max_length),
+        num_workers=0,
+        shuffle=False,
+    )
+
+    plt.figure(figsize=(10, 5), dpi=200)
+
+    plt.xlabel("Frame")
+    plt.ylabel("Loss")
+    plt.yscale("log")
+    plt.title("Semantic Loss")
+    plt.grid(which="both", axis="both")
+    plt.xlim(0, max_length)
+
+    tests = [
+        (
+            "pertrain-medium",
+            "dual_ar_2_codebook_medium",
+            "checkpoints/text2semantic-pretrain-medium-2k-v1.pth",
+        ),
+        (
+            "sft-medium",
+            "dual_ar_2_codebook_medium",
+            "checkpoints/text2semantic-sft-medium-v1.1-4k.pth",
+        ),
+        (
+            "sft-large",
+            "dual_ar_2_codebook_large",
+            "checkpoints/text2semantic-sft-large-v1.1-4k.pth",
+        ),
+    ]
+
+    for name, config, weight in tests:
+        xs, _, smoothed_ys = analyze_one_model(loader, config, weight, max_length)
+        plt.plot(xs, smoothed_ys, label=name)
+
+    plt.legend()
+    plt.savefig("semantic_loss.png")
+
+
+if __name__ == "__main__":
+    main()