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

xinference/thirdparty/fish_speech/tools/whisper_asr.py

@@ -0,0 +1,176 @@
+"""
+Used to transcribe all audio files in one folder into another folder.
+e.g.
+Directory structure:
+--pre_data_root
+----SP_1
+------01.wav
+------02.wav
+------......
+----SP_2
+------01.wav
+------02.wav
+------......
+Use 
+python tools/whisper_asr.py --audio-dir pre_data_root/SP_1 --save-dir data/SP_1 
+to transcribe the first speaker.
+
+Use 
+python tools/whisper_asr.py --audio-dir pre_data_root/SP_2 --save-dir data/SP_2 
+to transcribe the second speaker.
+
+Note: Be aware of your audio sample rate, which defaults to 44.1kHz.
+"""
+
+import re
+from pathlib import Path
+
+import click
+import soundfile as sf
+from faster_whisper import WhisperModel
+from loguru import logger
+from pydub import AudioSegment
+from tqdm import tqdm
+
+from tools.file import AUDIO_EXTENSIONS, list_files
+
+
+@click.command()
+@click.option("--model-size", default="large-v3", help="Size of the Whisper model")
+@click.option(
+    "--compute-type",
+    default="float16",
+    help="Computation Precision of the Whisper model [float16 / int8_float16 / int8]",
+)
+@click.option("--audio-dir", required=True, help="Directory containing audio files")
+@click.option(
+    "--save-dir", required=True, help="Directory to save processed audio files"
+)
+@click.option(
+    "--sample-rate",
+    default=44100,
+    type=int,
+    help="Output sample rate, default to input sample rate",
+)
+@click.option("--device", default="cuda", help="Device to use [cuda / cpu]")
+@click.option("--language", default="auto", help="Language of the transcription")
+@click.option("--initial-prompt", default=None, help="Initial prompt for transcribing")
+def main(
+    model_size,
+    compute_type,
+    audio_dir,
+    save_dir,
+    sample_rate,
+    device,
+    language,
+    initial_prompt,
+):
+    logger.info("Loading / Downloading Faster Whisper model...")
+
+    model = WhisperModel(
+        model_size,
+        device=device,
+        compute_type=compute_type,
+        download_root="faster_whisper",
+    )
+
+    logger.info("Model loaded.")
+
+    save_path = Path(save_dir)
+    save_path.mkdir(parents=True, exist_ok=True)
+
+    audio_files = list_files(
+        path=audio_dir, extensions=AUDIO_EXTENSIONS, recursive=True
+    )
+
+    for file_path in tqdm(audio_files, desc="Processing audio file"):
+        file_stem = file_path.stem
+        file_suffix = file_path.suffix
+
+        rel_path = Path(file_path).relative_to(audio_dir)
+        (save_path / rel_path.parent).mkdir(parents=True, exist_ok=True)
+
+        audio = AudioSegment.from_file(file_path)
+
+        segments, info = model.transcribe(
+            file_path,
+            beam_size=5,
+            language=None if language == "auto" else language,
+            initial_prompt=initial_prompt,
+        )
+
+        print(
+            "Detected language '%s' with probability %f"
+            % (info.language, info.language_probability)
+        )
+        print("Total len(ms): ", len(audio))
+
+        whole_text = None
+        for segment in segments:
+            id, start, end, text = (
+                segment.id,
+                segment.start,
+                segment.end,
+                segment.text,
+            )
+            print("Segment %03d [%.2fs -> %.2fs] %s" % (id, start, end, text))
+            if not whole_text:
+                whole_text = text
+            else:
+                whole_text += ", " + text
+
+        whole_text += "."
+
+        audio_save_path = save_path / rel_path.parent / f"{file_stem}{file_suffix}"
+        audio.export(audio_save_path, format=file_suffix[1:])
+        print(f"Exported {audio_save_path}")
+
+        transcript_save_path = save_path / rel_path.parent / f"{file_stem}.lab"
+        with open(
+            transcript_save_path,
+            "w",
+            encoding="utf-8",
+        ) as f:
+            f.write(whole_text)
+
+
+if __name__ == "__main__":
+    main()
+    exit(0)
+
+    audio = AudioSegment.from_wav(
+        r"D:\PythonProject\原神语音中文\胡桃\vo_hutao_draw_appear.wav"
+    )
+
+    model_size = "large-v3"
+
+    model = WhisperModel(
+        model_size,
+        device="cuda",
+        compute_type="float16",
+        download_root="faster_whisper",
+    )
+
+    segments, info = model.transcribe(
+        r"D:\PythonProject\原神语音中文\胡桃\vo_hutao_draw_appear.wav",
+        beam_size=5,
+    )
+
+    print(
+        "Detected language '%s' with probability %f"
+        % (info.language, info.language_probability)
+    )
+    print("Total len(ms): ", len(audio))
+
+    for i, segment in enumerate(segments):
+        print(
+            "Segment %03d [%.2fs -> %.2fs] %s"
+            % (i, segment.start, segment.end, segment.text)
+        )
+        start_ms = int(segment.start * 1000)
+        end_ms = int(segment.end * 1000)
+        segment_audio = audio[start_ms:end_ms]
+        segment_audio.export(f"segment_{i:03d}.wav", format="wav")
+        print(f"Exported segment_{i:03d}.wav")
+
+    print("All segments have been exported.")

xinference/thirdparty/internvl/conversation.py

@@ -0,0 +1,393 @@
+"""
+Conversation prompt templates.
+
+We kindly request that you import fastchat instead of copying this file if you wish to use it.
+If you have changes in mind, please contribute back so the community can benefit collectively and continue to maintain these valuable templates.
+"""
+
+import dataclasses
+from enum import IntEnum, auto
+from typing import Any, Dict, List, Tuple, Union
+
+
+class SeparatorStyle(IntEnum):
+    """Separator styles."""
+
+    ADD_COLON_SINGLE = auto()
+    ADD_COLON_TWO = auto()
+    ADD_COLON_SPACE_SINGLE = auto()
+    NO_COLON_SINGLE = auto()
+    NO_COLON_TWO = auto()
+    ADD_NEW_LINE_SINGLE = auto()
+    LLAMA2 = auto()
+    CHATGLM = auto()
+    CHATML = auto()
+    CHATINTERN = auto()
+    DOLLY = auto()
+    RWKV = auto()
+    PHOENIX = auto()
+    ROBIN = auto()
+    FALCON_CHAT = auto()
+    CHATGLM3 = auto()
+    INTERNVL_ZH = auto()
+    MPT = auto()
+
+
+@dataclasses.dataclass
+class Conversation:
+    """A class that manages prompt templates and keeps all conversation history."""
+
+    # The name of this template
+    name: str
+    # The template of the system prompt
+    system_template: str = '{system_message}'
+    # The system message
+    system_message: str = ''
+    # The names of two roles
+    roles: Tuple[str] = ('USER', 'ASSISTANT')
+    # All messages. Each item is (role, message).
+    messages: List[List[str]] = ()
+    # The number of few shot examples
+    offset: int = 0
+    # The separator style and configurations
+    sep_style: SeparatorStyle = SeparatorStyle.ADD_COLON_SINGLE
+    sep: str = '\n'
+    sep2: str = None
+    # Stop criteria (the default one is EOS token)
+    stop_str: Union[str, List[str]] = None
+    # Stops generation if meeting any token in this list
+    stop_token_ids: List[int] = None
+
+    def get_prompt(self) -> str:
+        """Get the prompt for generation."""
+        system_prompt = self.system_template.format(system_message=self.system_message)
+        if self.sep_style == SeparatorStyle.ADD_COLON_SINGLE:
+            ret = system_prompt + self.sep
+            for role, message in self.messages:
+                if message:
+                    ret += role + ': ' + message + self.sep
+                else:
+                    ret += role + ':'
+            return ret
+        elif self.sep_style == SeparatorStyle.ADD_COLON_TWO:
+            seps = [self.sep, self.sep2]
+            ret = system_prompt + seps[0]
+            for i, (role, message) in enumerate(self.messages):
+                if message:
+                    ret += role + ': ' + message + seps[i % 2]
+                else:
+                    ret += role + ':'
+            return ret
+        elif self.sep_style == SeparatorStyle.ADD_COLON_SPACE_SINGLE:
+            ret = system_prompt + self.sep
+            for role, message in self.messages:
+                if message:
+                    ret += role + ': ' + message + self.sep
+                else:
+                    ret += role + ': '  # must be end with a space
+            return ret
+        elif self.sep_style == SeparatorStyle.ADD_NEW_LINE_SINGLE:
+            ret = '' if system_prompt == '' else system_prompt + self.sep
+            for role, message in self.messages:
+                if message:
+                    ret += role + '\n' + message + self.sep
+                else:
+                    ret += role + '\n'
+            return ret
+        elif self.sep_style == SeparatorStyle.NO_COLON_SINGLE:
+            ret = system_prompt
+            for role, message in self.messages:
+                if message:
+                    ret += role + message + self.sep
+                else:
+                    ret += role
+            return ret
+        elif self.sep_style == SeparatorStyle.NO_COLON_TWO:
+            seps = [self.sep, self.sep2]
+            ret = system_prompt
+            for i, (role, message) in enumerate(self.messages):
+                if message:
+                    ret += role + message + seps[i % 2]
+                else:
+                    ret += role
+            return ret
+        elif self.sep_style == SeparatorStyle.RWKV:
+            ret = system_prompt
+            for i, (role, message) in enumerate(self.messages):
+                if message:
+                    ret += (
+                        role
+                        + ': '
+                        + message.replace('\r\n', '\n').replace('\n\n', '\n')
+                    )
+                    ret += '\n\n'
+                else:
+                    ret += role + ':'
+            return ret
+        elif self.sep_style == SeparatorStyle.LLAMA2:
+            seps = [self.sep, self.sep2]
+            if self.system_message:
+                ret = system_prompt
+            else:
+                ret = '[INST] '
+            for i, (role, message) in enumerate(self.messages):
+                tag = self.roles[i % 2]
+                if message:
+                    if i == 0:
+                        ret += message + ' '
+                    else:
+                        ret += tag + ' ' + message + seps[i % 2]
+                else:
+                    ret += tag
+            return ret
+        elif self.sep_style == SeparatorStyle.CHATGLM:
+            # source: https://huggingface.co/THUDM/chatglm-6b/blob/1d240ba371910e9282298d4592532d7f0f3e9f3e/modeling_chatglm.py#L1302-L1308
+            # source2: https://huggingface.co/THUDM/chatglm2-6b/blob/e186c891cf64310ac66ef10a87e6635fa6c2a579/modeling_chatglm.py#L926
+            round_add_n = 1 if self.name == 'chatglm2' else 0
+            if system_prompt:
+                ret = system_prompt + self.sep
+            else:
+                ret = ''
+
+            for i, (role, message) in enumerate(self.messages):
+                if i % 2 == 0:
+                    ret += f'[Round {i//2 + round_add_n}]{self.sep}'
+
+                if message:
+                    ret += f'{role}：{message}{self.sep}'
+                else:
+                    ret += f'{role}：'
+            return ret
+        elif self.sep_style == SeparatorStyle.CHATML:
+            ret = '' if system_prompt == '' else system_prompt + self.sep + '\n'
+            for role, message in self.messages:
+                if message:
+                    ret += role + '\n' + message + self.sep + '\n'
+                else:
+                    ret += role + '\n'
+            return ret
+        elif self.sep_style == SeparatorStyle.CHATGLM3:
+            ret = ''
+            if self.system_message:
+                ret += system_prompt
+            for role, message in self.messages:
+                if message:
+                    ret += role + '\n' + ' ' + message
+                else:
+                    ret += role
+            return ret
+        elif self.sep_style == SeparatorStyle.CHATINTERN:
+            # source: https://huggingface.co/internlm/internlm-chat-7b-8k/blob/bd546fa984b4b0b86958f56bf37f94aa75ab8831/modeling_internlm.py#L771
+            seps = [self.sep, self.sep2]
+            ret = system_prompt
+            for i, (role, message) in enumerate(self.messages):
+                # if i % 2 == 0:
+                #     ret += "<s>"
+                if message:
+                    ret += role + ':' + message + seps[i % 2] + '\n'
+                else:
+                    ret += role + ':'
+            return ret
+        elif self.sep_style == SeparatorStyle.DOLLY:
+            seps = [self.sep, self.sep2]
+            ret = system_prompt
+            for i, (role, message) in enumerate(self.messages):
+                if message:
+                    ret += role + ':\n' + message + seps[i % 2]
+                    if i % 2 == 1:
+                        ret += '\n\n'
+                else:
+                    ret += role + ':\n'
+            return ret
+        elif self.sep_style == SeparatorStyle.PHOENIX:
+            ret = system_prompt
+            for role, message in self.messages:
+                if message:
+                    ret += role + ': ' + '<s>' + message + '</s>'
+                else:
+                    ret += role + ': ' + '<s>'
+            return ret
+        elif self.sep_style == SeparatorStyle.ROBIN:
+            ret = system_prompt + self.sep
+            for role, message in self.messages:
+                if message:
+                    ret += role + ':\n' + message + self.sep
+                else:
+                    ret += role + ':\n'
+            return ret
+        elif self.sep_style == SeparatorStyle.FALCON_CHAT:
+            ret = ''
+            if self.system_message:
+                ret += system_prompt + self.sep
+            for role, message in self.messages:
+                if message:
+                    ret += role + ': ' + message + self.sep
+                else:
+                    ret += role + ':'
+
+            return ret
+        elif self.sep_style == SeparatorStyle.INTERNVL_ZH:
+            seps = [self.sep, self.sep2]
+            ret = self.system_message + seps[0]
+            for i, (role, message) in enumerate(self.messages):
+                if message:
+                    ret += role + ': ' + message + seps[i % 2]
+                else:
+                    ret += role + ':'
+            return ret
+        elif self.sep_style == SeparatorStyle.MPT:
+            ret = system_prompt + self.sep
+            for role, message in self.messages:
+                if message:
+                    if type(message) is tuple:
+                        message, _, _ = message
+                    ret += role + message + self.sep
+                else:
+                    ret += role
+            return ret
+        else:
+            raise ValueError(f'Invalid style: {self.sep_style}')
+
+    def set_system_message(self, system_message: str):
+        """Set the system message."""
+        self.system_message = system_message
+
+    def append_message(self, role: str, message: str):
+        """Append a new message."""
+        self.messages.append([role, message])
+
+    def update_last_message(self, message: str):
+        """Update the last output.
+
+        The last message is typically set to be None when constructing the prompt,
+        so we need to update it in-place after getting the response from a model.
+        """
+        self.messages[-1][1] = message
+
+    def to_gradio_chatbot(self):
+        """Convert the conversation to gradio chatbot format."""
+        ret = []
+        for i, (role, msg) in enumerate(self.messages[self.offset :]):
+            if i % 2 == 0:
+                ret.append([msg, None])
+            else:
+                ret[-1][-1] = msg
+        return ret
+
+    def to_openai_api_messages(self):
+        """Convert the conversation to OpenAI chat completion format."""
+        ret = [{'role': 'system', 'content': self.system_message}]
+
+        for i, (_, msg) in enumerate(self.messages[self.offset :]):
+            if i % 2 == 0:
+                ret.append({'role': 'user', 'content': msg})
+            else:
+                if msg is not None:
+                    ret.append({'role': 'assistant', 'content': msg})
+        return ret
+
+    def copy(self):
+        return Conversation(
+            name=self.name,
+            system_template=self.system_template,
+            system_message=self.system_message,
+            roles=self.roles,
+            messages=[[x, y] for x, y in self.messages],
+            offset=self.offset,
+            sep_style=self.sep_style,
+            sep=self.sep,
+            sep2=self.sep2,
+            stop_str=self.stop_str,
+            stop_token_ids=self.stop_token_ids,
+        )
+
+    def dict(self):
+        return {
+            'template_name': self.name,
+            'system_message': self.system_message,
+            'roles': self.roles,
+            'messages': self.messages,
+            'offset': self.offset,
+        }
+
+
+# A global registry for all conversation templates
+conv_templates: Dict[str, Conversation] = {}
+
+
+def register_conv_template(template: Conversation, override: bool = False):
+    """Register a new conversation template."""
+    if not override:
+        assert (
+            template.name not in conv_templates
+        ), f'{template.name} has been registered.'
+
+    conv_templates[template.name] = template
+
+
+def get_conv_template(name: str) -> Conversation:
+    """Get a conversation template."""
+    return conv_templates[name].copy()
+
+
+# Both Hermes-2 and internlm2-chat are chatml-format conversation templates. The difference
+# is that during training, the preprocessing function for the Hermes-2 template doesn't add
+# <s> at the beginning of the tokenized sequence, while the internlm2-chat template does.
+# Therefore, they are completely equivalent during inference.
+register_conv_template(
+    Conversation(
+        name='Hermes-2',
+        system_template='<|im_start|>system\n{system_message}',
+        # note: The new system prompt was not used here to avoid changes in benchmark performance.
+        # system_message='我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。',
+        system_message='你是由上海人工智能实验室联合商汤科技开发的书生多模态大模型，英文名叫InternVL, 是一个有用无害的人工智能助手。',
+        roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
+        sep_style=SeparatorStyle.MPT,
+        sep='<|im_end|>',
+        stop_token_ids=[
+            2,
+            6,
+            7,
+            8,
+        ],
+        stop_str='<|endoftext|>',
+    )
+)
+
+
+register_conv_template(
+    Conversation(
+        name='internlm2-chat',
+        system_template='<|im_start|>system\n{system_message}',
+        # note: The new system prompt was not used here to avoid changes in benchmark performance.
+        # system_message='我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。',
+        system_message='你是由上海人工智能实验室联合商汤科技开发的书生多模态大模型，英文名叫InternVL, 是一个有用无害的人工智能助手。',
+        roles=('<|im_start|>user\n', '<|im_start|>assistant\n'),
+        sep_style=SeparatorStyle.MPT,
+        sep='<|im_end|>',
+        stop_token_ids=[
+            2,
+            92543,
+            92542
+        ]
+    )
+)
+
+
+register_conv_template(
+    Conversation(
+        name='phi3-chat',
+        system_template='<|system|>\n{system_message}',
+        # note: The new system prompt was not used here to avoid changes in benchmark performance.
+        # system_message='我是书生·万象，英文名是InternVL，是由上海人工智能实验室、清华大学及多家合作单位联合开发的多模态大语言模型。',
+        system_message='你是由上海人工智能实验室联合商汤科技开发的书生多模态大模型，英文名叫InternVL, 是一个有用无害的人工智能助手。',
+        roles=('<|user|>\n', '<|assistant|>\n'),
+        sep_style=SeparatorStyle.MPT,
+        sep='<|end|>',
+        stop_token_ids=[
+            2,
+            32000,
+            32007
+        ]
+    )
+)

xinference/thirdparty/omnilmm/model/utils.py

@@ -3,7 +3,6 @@ import os
 import pickle
 from io import BytesIO
 
-import cv2
 import numpy as np
 import torch
 import torch.distributed as dist
@@ -75,6 +74,8 @@ def autocontrast_func(img, cutoff=0):
     """
     same output as PIL.ImageOps.autocontrast
     """
+    import cv2
+
     n_bins = 256
 
     def tune_channel(ch):
@@ -108,6 +109,8 @@ def equalize_func(img):
     same output as PIL.ImageOps.equalize
     PIL's implementation is different from cv2.equalize
     """
+    import cv2
+
     n_bins = 256
 
     def tune_channel(ch):
@@ -131,6 +134,8 @@ def rotate_func(img, degree, fill=(0, 0, 0)):
     """
     like PIL, rotate by degree, not radians
     """
+    import cv2
+
     H, W = img.shape[0], img.shape[1]
     center = W / 2, H / 2
     M = cv2.getRotationMatrix2D(center, degree, 1)
@@ -194,6 +199,8 @@ def sharpness_func(img, factor):
     The differences the this result and PIL are all on the 4 boundaries, the center
     areas are same
     """
+    import cv2
+
     kernel = np.ones((3, 3), dtype=np.float32)
     kernel[1][1] = 5
     kernel /= 13
@@ -211,6 +218,8 @@ def sharpness_func(img, factor):
 
 
 def shear_x_func(img, factor, fill=(0, 0, 0)):
+    import cv2
+
     H, W = img.shape[0], img.shape[1]
     M = np.float32([[1, factor, 0], [0, 1, 0]])
     out = cv2.warpAffine(
@@ -223,6 +232,8 @@ def translate_x_func(img, offset, fill=(0, 0, 0)):
     """
     same output as PIL.Image.transform
     """
+    import cv2
+
     H, W = img.shape[0], img.shape[1]
     M = np.float32([[1, 0, -offset], [0, 1, 0]])
     out = cv2.warpAffine(
@@ -235,6 +246,8 @@ def translate_y_func(img, offset, fill=(0, 0, 0)):
     """
     same output as PIL.Image.transform
     """
+    import cv2
+
     H, W = img.shape[0], img.shape[1]
     M = np.float32([[1, 0, 0], [0, 1, -offset]])
     out = cv2.warpAffine(
@@ -252,6 +265,8 @@ def posterize_func(img, bits):
 
 
 def shear_y_func(img, factor, fill=(0, 0, 0)):
+    import cv2
+
     H, W = img.shape[0], img.shape[1]
     M = np.float32([[1, 0, 0], [factor, 1, 0]])
     out = cv2.warpAffine(

xinference/web/ui/build/asset-manifest.json

@@ -1,14 +1,14 @@
 {
   "files": {
     "main.css": "./static/css/main.4bafd904.css",
-    "main.js": "./static/js/main.17ca0398.js",
+    "main.js": "./static/js/main.661c7b0a.js",
     "static/media/icon.webp": "./static/media/icon.4603d52c63041e5dfbfd.webp",
     "index.html": "./index.html",
     "main.4bafd904.css.map": "./static/css/main.4bafd904.css.map",
-    "main.17ca0398.js.map": "./static/js/main.17ca0398.js.map"
+    "main.661c7b0a.js.map": "./static/js/main.661c7b0a.js.map"
   },
   "entrypoints": [
     "static/css/main.4bafd904.css",
-    "static/js/main.17ca0398.js"
+    "static/js/main.661c7b0a.js"
   ]
 }

xinference/web/ui/build/index.html

@@ -1 +1 @@
-<!doctype html><html lang="en"><head><meta charset="utf-8"/><link rel="icon" href="./favicon.svg"/><meta name="viewport" content="width=device-width,initial-scale=1"/><meta name="theme-color" content="#000000"/><meta name="description" content="Web site created using create-react-app"/><link rel="apple-touch-icon" href="./logo192.png"/><link rel="manifest" href="./manifest.json"/><title>Xinference</title><script defer="defer" src="./static/js/main.17ca0398.js"></script><link href="./static/css/main.4bafd904.css" rel="stylesheet"></head><body><noscript>You need to enable JavaScript to run this app.</noscript><div id="root"></div></body></html>
+<!doctype html><html lang="en"><head><meta charset="utf-8"/><link rel="icon" href="./favicon.svg"/><meta name="viewport" content="width=device-width,initial-scale=1"/><meta name="theme-color" content="#000000"/><meta name="description" content="Web site created using create-react-app"/><link rel="apple-touch-icon" href="./logo192.png"/><link rel="manifest" href="./manifest.json"/><title>Xinference</title><script defer="defer" src="./static/js/main.661c7b0a.js"></script><link href="./static/css/main.4bafd904.css" rel="stylesheet"></head><body><noscript>You need to enable JavaScript to run this app.</noscript><div id="root"></div></body></html>