mirror of
https://github.com/index-tts/index-tts.git
synced 2025-11-28 02:10:23 +08:00
ec368de932
- We can't use the original "Show experimental features" checkbox implementation, because it *deeply* breaks Gradio.
- Gradio's `gr.Examples()` API binds itself to the original state of the user interface. Gradio crashes and causes various bugs if we try to change the available UI controls later.
- Instead, we must use `gr.Dataset()` which acts like a custom input/output control and doesn't directly bind itself to the target control. We must also provide a secret, hidden "all mode choices" component so that it knows the names of all "control modes" that are possible in examples.
- We now also have a very visible warning label in the user interface, to clearly mark the experimental features.
- Bugs fixed:
* The code was unable to toggle the visibility of Experimental demos in the Examples list. It was not possible with Examples (since it's a wrapper around Dataset, but Examples contains its own internal state/copy of all data). Instead, we use a Dataset and manipulate its list directly.
* Gradio crashes with a `gradio.exceptions.Error` exception if you try to load an example that tries to use an experimental feature if we have removed its UI element. This is because Examples binds to the original user interface and *remembers* the list of choices, and it *cannot* dynamically select something that did not exist when the `gr.Examples()` was initially created. This problem is fixed by switching to `gr.Dataset()`.
* Furthermore, Gradio's `gr.Examples()` handler actually remembers and caches the list of UI options. So every time we load an example, it rewrites the "Emotion Control Mode" selection menu to only show the options that were available when the Examples table was created. This means that even if we keep the "Show experimental features" checkbox, Gradio itself will erase the experimental mode from the Control Mode selection menu every time the user loads an example. There are no callbacks or "update" functions to allow us to override this automatic Gradio behavior. But by switching to `gr.Dataset()`, we completely avoid this deep binding.
* The "Show experimental features" checkbox is no longer tied to a column in the examples-table, to avoid fighting between Gradio's example table trying to set the mode, and the experimental checkbox being toggled and also trying to set the mode.
* Lastly, the "Show experimental features" checkbox now remembers and restores the user's current mode selection when toggling the checkbox, instead of constantly resetting to the default mode ("same as voice reference"), to make the UI more convenient for users.
442 lines
21 KiB
Python
442 lines
21 KiB
Python
import html
|
||
import json
|
||
import os
|
||
import sys
|
||
import threading
|
||
import time
|
||
|
||
import warnings
|
||
|
||
warnings.filterwarnings("ignore", category=FutureWarning)
|
||
warnings.filterwarnings("ignore", category=UserWarning)
|
||
|
||
import pandas as pd
|
||
|
||
current_dir = os.path.dirname(os.path.abspath(__file__))
|
||
sys.path.append(current_dir)
|
||
sys.path.append(os.path.join(current_dir, "indextts"))
|
||
|
||
import argparse
|
||
parser = argparse.ArgumentParser(
|
||
description="IndexTTS WebUI",
|
||
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
|
||
)
|
||
parser.add_argument("--verbose", action="store_true", default=False, help="Enable verbose mode")
|
||
parser.add_argument("--port", type=int, default=7860, help="Port to run the web UI on")
|
||
parser.add_argument("--host", type=str, default="0.0.0.0", help="Host to run the web UI on")
|
||
parser.add_argument("--model_dir", type=str, default="./checkpoints", help="Model checkpoints directory")
|
||
parser.add_argument("--fp16", action="store_true", default=False, help="Use FP16 for inference if available")
|
||
parser.add_argument("--deepspeed", action="store_true", default=False, help="Use DeepSpeed to accelerate if available")
|
||
parser.add_argument("--cuda_kernel", action="store_true", default=False, help="Use CUDA kernel for inference if available")
|
||
parser.add_argument("--gui_seg_tokens", type=int, default=120, help="GUI: Max tokens per generation segment")
|
||
cmd_args = parser.parse_args()
|
||
|
||
if not os.path.exists(cmd_args.model_dir):
|
||
print(f"Model directory {cmd_args.model_dir} does not exist. Please download the model first.")
|
||
sys.exit(1)
|
||
|
||
for file in [
|
||
"bpe.model",
|
||
"gpt.pth",
|
||
"config.yaml",
|
||
"s2mel.pth",
|
||
"wav2vec2bert_stats.pt"
|
||
]:
|
||
file_path = os.path.join(cmd_args.model_dir, file)
|
||
if not os.path.exists(file_path):
|
||
print(f"Required file {file_path} does not exist. Please download it.")
|
||
sys.exit(1)
|
||
|
||
import gradio as gr
|
||
from indextts.infer_v2 import IndexTTS2
|
||
from tools.i18n.i18n import I18nAuto
|
||
|
||
i18n = I18nAuto(language="Auto")
|
||
MODE = 'local'
|
||
tts = IndexTTS2(model_dir=cmd_args.model_dir,
|
||
cfg_path=os.path.join(cmd_args.model_dir, "config.yaml"),
|
||
use_fp16=cmd_args.fp16,
|
||
use_deepspeed=cmd_args.deepspeed,
|
||
use_cuda_kernel=cmd_args.cuda_kernel,
|
||
)
|
||
# 支持的语言列表
|
||
LANGUAGES = {
|
||
"中文": "zh_CN",
|
||
"English": "en_US"
|
||
}
|
||
EMO_CHOICES_ALL = [i18n("与音色参考音频相同"),
|
||
i18n("使用情感参考音频"),
|
||
i18n("使用情感向量控制"),
|
||
i18n("使用情感描述文本控制")]
|
||
EMO_CHOICES_OFFICIAL = EMO_CHOICES_ALL[:-1] # skip experimental features
|
||
|
||
os.makedirs("outputs/tasks",exist_ok=True)
|
||
os.makedirs("prompts",exist_ok=True)
|
||
|
||
MAX_LENGTH_TO_USE_SPEED = 70
|
||
example_cases = []
|
||
with open("examples/cases.jsonl", "r", encoding="utf-8") as f:
|
||
for line in f:
|
||
line = line.strip()
|
||
if not line:
|
||
continue
|
||
example = json.loads(line)
|
||
if example.get("emo_audio",None):
|
||
emo_audio_path = os.path.join("examples",example["emo_audio"])
|
||
else:
|
||
emo_audio_path = None
|
||
|
||
example_cases.append([os.path.join("examples", example.get("prompt_audio", "sample_prompt.wav")),
|
||
EMO_CHOICES_ALL[example.get("emo_mode",0)],
|
||
example.get("text"),
|
||
emo_audio_path,
|
||
example.get("emo_weight",1.0),
|
||
example.get("emo_text",""),
|
||
example.get("emo_vec_1",0),
|
||
example.get("emo_vec_2",0),
|
||
example.get("emo_vec_3",0),
|
||
example.get("emo_vec_4",0),
|
||
example.get("emo_vec_5",0),
|
||
example.get("emo_vec_6",0),
|
||
example.get("emo_vec_7",0),
|
||
example.get("emo_vec_8",0),
|
||
])
|
||
|
||
def get_example_cases(include_experimental = False):
|
||
if include_experimental:
|
||
return example_cases # show every example
|
||
|
||
# exclude emotion control mode 3 (emotion from text description)
|
||
return [x for x in example_cases if x[1] != EMO_CHOICES_ALL[3]]
|
||
|
||
def gen_single(emo_control_method,prompt, text,
|
||
emo_ref_path, emo_weight,
|
||
vec1, vec2, vec3, vec4, vec5, vec6, vec7, vec8,
|
||
emo_text,emo_random,
|
||
max_text_tokens_per_segment=120,
|
||
*args, progress=gr.Progress()):
|
||
output_path = None
|
||
if not output_path:
|
||
output_path = os.path.join("outputs", f"spk_{int(time.time())}.wav")
|
||
# set gradio progress
|
||
tts.gr_progress = progress
|
||
do_sample, top_p, top_k, temperature, \
|
||
length_penalty, num_beams, repetition_penalty, max_mel_tokens = args
|
||
kwargs = {
|
||
"do_sample": bool(do_sample),
|
||
"top_p": float(top_p),
|
||
"top_k": int(top_k) if int(top_k) > 0 else None,
|
||
"temperature": float(temperature),
|
||
"length_penalty": float(length_penalty),
|
||
"num_beams": num_beams,
|
||
"repetition_penalty": float(repetition_penalty),
|
||
"max_mel_tokens": int(max_mel_tokens),
|
||
# "typical_sampling": bool(typical_sampling),
|
||
# "typical_mass": float(typical_mass),
|
||
}
|
||
if type(emo_control_method) is not int:
|
||
emo_control_method = emo_control_method.value
|
||
if emo_control_method == 0: # emotion from speaker
|
||
emo_ref_path = None # remove external reference audio
|
||
if emo_control_method == 1: # emotion from reference audio
|
||
pass
|
||
if emo_control_method == 2: # emotion from custom vectors
|
||
vec = [vec1, vec2, vec3, vec4, vec5, vec6, vec7, vec8]
|
||
vec = tts.normalize_emo_vec(vec, apply_bias=True)
|
||
else:
|
||
# don't use the emotion vector inputs for the other modes
|
||
vec = None
|
||
|
||
if emo_text == "":
|
||
# erase empty emotion descriptions; `infer()` will then automatically use the main prompt
|
||
emo_text = None
|
||
|
||
print(f"Emo control mode:{emo_control_method},weight:{emo_weight},vec:{vec}")
|
||
output = tts.infer(spk_audio_prompt=prompt, text=text,
|
||
output_path=output_path,
|
||
emo_audio_prompt=emo_ref_path, emo_alpha=emo_weight,
|
||
emo_vector=vec,
|
||
use_emo_text=(emo_control_method==3), emo_text=emo_text,use_random=emo_random,
|
||
verbose=cmd_args.verbose,
|
||
max_text_tokens_per_segment=int(max_text_tokens_per_segment),
|
||
**kwargs)
|
||
return gr.update(value=output,visible=True)
|
||
|
||
def update_prompt_audio():
|
||
update_button = gr.update(interactive=True)
|
||
return update_button
|
||
|
||
def create_warning_message(warning_text):
|
||
return gr.HTML(f"<div style=\"padding: 0.5em 0.8em; border-radius: 0.5em; background: #ffa87d; color: #000; font-weight: bold\">{html.escape(warning_text)}</div>")
|
||
|
||
def create_experimental_warning_message():
|
||
return create_warning_message(i18n('提示：此功能为实验版，结果尚不稳定，我们正在持续优化中。'))
|
||
|
||
with gr.Blocks(title="IndexTTS Demo") as demo:
|
||
mutex = threading.Lock()
|
||
gr.HTML('''
|
||
<h2><center>IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech</h2>
|
||
<p align="center">
|
||
<a href='https://arxiv.org/abs/2506.21619'><img src='https://img.shields.io/badge/ArXiv-2506.21619-red'></a>
|
||
</p>
|
||
''')
|
||
|
||
with gr.Tab(i18n("音频生成")):
|
||
with gr.Row():
|
||
os.makedirs("prompts",exist_ok=True)
|
||
prompt_audio = gr.Audio(label=i18n("音色参考音频"),key="prompt_audio",
|
||
sources=["upload","microphone"],type="filepath")
|
||
prompt_list = os.listdir("prompts")
|
||
default = ''
|
||
if prompt_list:
|
||
default = prompt_list[0]
|
||
with gr.Column():
|
||
input_text_single = gr.TextArea(label=i18n("文本"),key="input_text_single", placeholder=i18n("请输入目标文本"), info=f"{i18n('当前模型版本')}{tts.model_version or '1.0'}")
|
||
gen_button = gr.Button(i18n("生成语音"), key="gen_button",interactive=True)
|
||
output_audio = gr.Audio(label=i18n("生成结果"), visible=True,key="output_audio")
|
||
|
||
experimental_checkbox = gr.Checkbox(label=i18n("显示实验功能"), value=False)
|
||
|
||
with gr.Accordion(i18n("功能设置")):
|
||
# 情感控制选项部分
|
||
with gr.Row():
|
||
emo_control_method = gr.Radio(
|
||
choices=EMO_CHOICES_OFFICIAL,
|
||
type="index",
|
||
value=EMO_CHOICES_OFFICIAL[0],label=i18n("情感控制方式"))
|
||
# we MUST have an extra, INVISIBLE list of *all* emotion control
|
||
# methods so that gr.Dataset() can fetch ALL control mode labels!
|
||
# otherwise, the gr.Dataset()'s experimental labels would be empty!
|
||
emo_control_method_all = gr.Radio(
|
||
choices=EMO_CHOICES_ALL,
|
||
type="index",
|
||
value=EMO_CHOICES_ALL[0], label=i18n("情感控制方式"),
|
||
visible=False) # do not render
|
||
# 情感参考音频部分
|
||
with gr.Group(visible=False) as emotion_reference_group:
|
||
with gr.Row():
|
||
emo_upload = gr.Audio(label=i18n("上传情感参考音频"), type="filepath")
|
||
|
||
# 情感随机采样
|
||
with gr.Row(visible=False) as emotion_randomize_group:
|
||
emo_random = gr.Checkbox(label=i18n("情感随机采样"), value=False)
|
||
|
||
# 情感向量控制部分
|
||
with gr.Group(visible=False) as emotion_vector_group:
|
||
with gr.Row():
|
||
with gr.Column():
|
||
vec1 = gr.Slider(label=i18n("喜"), minimum=0.0, maximum=1.0, value=0.0, step=0.05)
|
||
vec2 = gr.Slider(label=i18n("怒"), minimum=0.0, maximum=1.0, value=0.0, step=0.05)
|
||
vec3 = gr.Slider(label=i18n("哀"), minimum=0.0, maximum=1.0, value=0.0, step=0.05)
|
||
vec4 = gr.Slider(label=i18n("惧"), minimum=0.0, maximum=1.0, value=0.0, step=0.05)
|
||
with gr.Column():
|
||
vec5 = gr.Slider(label=i18n("厌恶"), minimum=0.0, maximum=1.0, value=0.0, step=0.05)
|
||
vec6 = gr.Slider(label=i18n("低落"), minimum=0.0, maximum=1.0, value=0.0, step=0.05)
|
||
vec7 = gr.Slider(label=i18n("惊喜"), minimum=0.0, maximum=1.0, value=0.0, step=0.05)
|
||
vec8 = gr.Slider(label=i18n("平静"), minimum=0.0, maximum=1.0, value=0.0, step=0.05)
|
||
|
||
with gr.Group(visible=False) as emo_text_group:
|
||
create_experimental_warning_message()
|
||
with gr.Row():
|
||
emo_text = gr.Textbox(label=i18n("情感描述文本"),
|
||
placeholder=i18n("请输入情绪描述（或留空以自动使用目标文本作为情绪描述）"),
|
||
value="",
|
||
info=i18n("例如：委屈巴巴、危险在悄悄逼近"))
|
||
|
||
with gr.Row(visible=False) as emo_weight_group:
|
||
emo_weight = gr.Slider(label=i18n("情感权重"), minimum=0.0, maximum=1.0, value=0.65, step=0.01)
|
||
|
||
with gr.Accordion(i18n("高级生成参数设置"), open=False, visible=True) as advanced_settings_group:
|
||
with gr.Row():
|
||
with gr.Column(scale=1):
|
||
gr.Markdown(f"**{i18n('GPT2 采样设置')}** _{i18n('参数会影响音频多样性和生成速度详见')} [Generation strategies](https://huggingface.co/docs/transformers/main/en/generation_strategies)._")
|
||
with gr.Row():
|
||
do_sample = gr.Checkbox(label="do_sample", value=True, info=i18n("是否进行采样"))
|
||
temperature = gr.Slider(label="temperature", minimum=0.1, maximum=2.0, value=0.8, step=0.1)
|
||
with gr.Row():
|
||
top_p = gr.Slider(label="top_p", minimum=0.0, maximum=1.0, value=0.8, step=0.01)
|
||
top_k = gr.Slider(label="top_k", minimum=0, maximum=100, value=30, step=1)
|
||
num_beams = gr.Slider(label="num_beams", value=3, minimum=1, maximum=10, step=1)
|
||
with gr.Row():
|
||
repetition_penalty = gr.Number(label="repetition_penalty", precision=None, value=10.0, minimum=0.1, maximum=20.0, step=0.1)
|
||
length_penalty = gr.Number(label="length_penalty", precision=None, value=0.0, minimum=-2.0, maximum=2.0, step=0.1)
|
||
max_mel_tokens = gr.Slider(label="max_mel_tokens", value=1500, minimum=50, maximum=tts.cfg.gpt.max_mel_tokens, step=10, info=i18n("生成Token最大数量，过小导致音频被截断"), key="max_mel_tokens")
|
||
# with gr.Row():
|
||
# typical_sampling = gr.Checkbox(label="typical_sampling", value=False, info="不建议使用")
|
||
# typical_mass = gr.Slider(label="typical_mass", value=0.9, minimum=0.0, maximum=1.0, step=0.1)
|
||
with gr.Column(scale=2):
|
||
gr.Markdown(f'**{i18n("分句设置")}** _{i18n("参数会影响音频质量和生成速度")}_')
|
||
with gr.Row():
|
||
initial_value = max(20, min(tts.cfg.gpt.max_text_tokens, cmd_args.gui_seg_tokens))
|
||
max_text_tokens_per_segment = gr.Slider(
|
||
label=i18n("分句最大Token数"), value=initial_value, minimum=20, maximum=tts.cfg.gpt.max_text_tokens, step=2, key="max_text_tokens_per_segment",
|
||
info=i18n("建议80~200之间，值越大，分句越长；值越小，分句越碎；过小过大都可能导致音频质量不高"),
|
||
)
|
||
with gr.Accordion(i18n("预览分句结果"), open=True) as segments_settings:
|
||
segments_preview = gr.Dataframe(
|
||
headers=[i18n("序号"), i18n("分句内容"), i18n("Token数")],
|
||
key="segments_preview",
|
||
wrap=True,
|
||
)
|
||
advanced_params = [
|
||
do_sample, top_p, top_k, temperature,
|
||
length_penalty, num_beams, repetition_penalty, max_mel_tokens,
|
||
# typical_sampling, typical_mass,
|
||
]
|
||
|
||
# we must use `gr.Dataset` to support dynamic UI rewrites, since `gr.Examples`
|
||
# binds tightly to UI and always restores the initial state of all components,
|
||
# such as the list of available choices in emo_control_method.
|
||
example_table = gr.Dataset(label="Examples",
|
||
samples_per_page=20,
|
||
samples=get_example_cases(include_experimental=False),
|
||
type="values",
|
||
# these components are NOT "connected". it just reads the column labels/available
|
||
# states from them, so we MUST link to the "all options" versions of all components,
|
||
# such as `emo_control_method_all` (to be able to see EXPERIMENTAL text labels)!
|
||
components=[prompt_audio,
|
||
emo_control_method_all, # important: support all mode labels!
|
||
input_text_single,
|
||
emo_upload,
|
||
emo_weight,
|
||
emo_text,
|
||
vec1, vec2, vec3, vec4, vec5, vec6, vec7, vec8]
|
||
)
|
||
|
||
def on_example_click(example):
|
||
print(f"Example clicked: ({len(example)} values) = {example!r}")
|
||
return (
|
||
gr.update(value=example[0]),
|
||
gr.update(value=example[1]),
|
||
gr.update(value=example[2]),
|
||
gr.update(value=example[3]),
|
||
gr.update(value=example[4]),
|
||
gr.update(value=example[5]),
|
||
gr.update(value=example[6]),
|
||
gr.update(value=example[7]),
|
||
gr.update(value=example[8]),
|
||
gr.update(value=example[9]),
|
||
gr.update(value=example[10]),
|
||
gr.update(value=example[11]),
|
||
gr.update(value=example[12]),
|
||
gr.update(value=example[13]),
|
||
)
|
||
|
||
# click() event works on both desktop and mobile UI
|
||
example_table.click(on_example_click,
|
||
inputs=[example_table],
|
||
outputs=[prompt_audio,
|
||
emo_control_method,
|
||
input_text_single,
|
||
emo_upload,
|
||
emo_weight,
|
||
emo_text,
|
||
vec1, vec2, vec3, vec4, vec5, vec6, vec7, vec8]
|
||
)
|
||
|
||
def on_input_text_change(text, max_text_tokens_per_segment):
|
||
if text and len(text) > 0:
|
||
text_tokens_list = tts.tokenizer.tokenize(text)
|
||
|
||
segments = tts.tokenizer.split_segments(text_tokens_list, max_text_tokens_per_segment=int(max_text_tokens_per_segment))
|
||
data = []
|
||
for i, s in enumerate(segments):
|
||
segment_str = ''.join(s)
|
||
tokens_count = len(s)
|
||
data.append([i, segment_str, tokens_count])
|
||
return {
|
||
segments_preview: gr.update(value=data, visible=True, type="array"),
|
||
}
|
||
else:
|
||
df = pd.DataFrame([], columns=[i18n("序号"), i18n("分句内容"), i18n("Token数")])
|
||
return {
|
||
segments_preview: gr.update(value=df),
|
||
}
|
||
|
||
def on_method_change(emo_control_method):
|
||
if emo_control_method == 1: # emotion reference audio
|
||
return (gr.update(visible=True),
|
||
gr.update(visible=False),
|
||
gr.update(visible=False),
|
||
gr.update(visible=False),
|
||
gr.update(visible=True)
|
||
)
|
||
elif emo_control_method == 2: # emotion vectors
|
||
return (gr.update(visible=False),
|
||
gr.update(visible=True),
|
||
gr.update(visible=True),
|
||
gr.update(visible=False),
|
||
gr.update(visible=True)
|
||
)
|
||
elif emo_control_method == 3: # emotion text description
|
||
return (gr.update(visible=False),
|
||
gr.update(visible=True),
|
||
gr.update(visible=False),
|
||
gr.update(visible=True),
|
||
gr.update(visible=True)
|
||
)
|
||
else: # 0: same as speaker voice
|
||
return (gr.update(visible=False),
|
||
gr.update(visible=False),
|
||
gr.update(visible=False),
|
||
gr.update(visible=False),
|
||
gr.update(visible=False)
|
||
)
|
||
|
||
emo_control_method.change(on_method_change,
|
||
inputs=[emo_control_method],
|
||
outputs=[emotion_reference_group,
|
||
emotion_randomize_group,
|
||
emotion_vector_group,
|
||
emo_text_group,
|
||
emo_weight_group]
|
||
)
|
||
|
||
def on_experimental_change(is_experimental, current_mode_index):
|
||
# 切换情感控制选项
|
||
new_choices = EMO_CHOICES_ALL if is_experimental else EMO_CHOICES_OFFICIAL
|
||
# if their current mode selection doesn't exist in new choices, reset to 0.
|
||
# we don't verify that OLD index means the same in NEW list, since we KNOW it does.
|
||
new_index = current_mode_index if current_mode_index < len(new_choices) else 0
|
||
|
||
return (
|
||
gr.update(choices=new_choices, value=new_choices[new_index]),
|
||
gr.update(samples=get_example_cases(include_experimental=is_experimental)),
|
||
)
|
||
|
||
experimental_checkbox.change(
|
||
on_experimental_change,
|
||
inputs=[experimental_checkbox, emo_control_method],
|
||
outputs=[emo_control_method, example_table]
|
||
)
|
||
|
||
input_text_single.change(
|
||
on_input_text_change,
|
||
inputs=[input_text_single, max_text_tokens_per_segment],
|
||
outputs=[segments_preview]
|
||
)
|
||
|
||
max_text_tokens_per_segment.change(
|
||
on_input_text_change,
|
||
inputs=[input_text_single, max_text_tokens_per_segment],
|
||
outputs=[segments_preview]
|
||
)
|
||
|
||
prompt_audio.upload(update_prompt_audio,
|
||
inputs=[],
|
||
outputs=[gen_button])
|
||
|
||
gen_button.click(gen_single,
|
||
inputs=[emo_control_method,prompt_audio, input_text_single, emo_upload, emo_weight,
|
||
vec1, vec2, vec3, vec4, vec5, vec6, vec7, vec8,
|
||
emo_text,emo_random,
|
||
max_text_tokens_per_segment,
|
||
*advanced_params,
|
||
],
|
||
outputs=[output_audio])
|
||
|
||
|
||
|
||
if __name__ == "__main__":
|
||
demo.queue(20)
|
||
demo.launch(server_name=cmd_args.host, server_port=cmd_args.port)
|