From af2b06e061937d291e276a0aa1bd4a2254a06078 Mon Sep 17 00:00:00 2001 From: nanaoto Date: Fri, 12 Sep 2025 14:20:04 +0800 Subject: [PATCH] =?UTF-8?q?feat:=20=E5=BD=92=E4=B8=80=E5=8C=96=E5=8F=82?= =?UTF-8?q?=E6=95=B0=E5=88=B0=E6=8E=A8=E8=8D=90=E7=9A=84=E8=8C=83=E5=9B=B4?= =?UTF-8?q?=EF=BC=8C=E6=94=B9=E5=96=84=E7=94=A8=E6=88=B7=E4=BD=93=E9=AA=8C?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- examples/cases.jsonl | 8 ++-- tools/i18n/locale/en_US.json | 5 +- tools/i18n/locale/zh_CN.json | 4 +- webui.py | 91 +++++++++++++++++++++++++++--------- 4 files changed, 78 insertions(+), 30 deletions(-) diff --git a/examples/cases.jsonl b/examples/cases.jsonl index 1b71672..32434ac 100644 --- a/examples/cases.jsonl +++ b/examples/cases.jsonl @@ -4,9 +4,9 @@ {"prompt_audio":"voice_04.wav","text":"你就需要我这种专业人士的帮助，就像手无缚鸡之力的人进入雪山狩猎，一定需要最老练的猎人指导。","emo_mode":0} {"prompt_audio":"voice_05.wav","text":"在真正的日本剑道中，格斗过程极其短暂，常常短至半秒，最长也不超过两秒，利剑相击的转瞬间，已有一方倒在血泊中。但在这电光石火的对决之前，双方都要以一个石雕般凝固的姿势站定，长时间的逼视对方，这一过程可能长达十分钟！","emo_mode":0} {"prompt_audio":"voice_06.wav","text":"今天呢，咱们开一部新书，叫《赛博朋克二零七七》。这词儿我听着都新鲜。这赛博朋克啊，简单理解就是“高科技，低生活”。这一听，我就明白了，于老师就爱用那高科技的东西，手机都得拿脚纹开，大冬天为了解锁脱得一丝不挂，冻得跟王八蛋似的。","emo_mode":0} -{"prompt_audio":"voice_07.wav","emo_audio":"emo_sad.wav","emo_weight": 0.9, "emo_mode":1,"text":"酒楼丧尽天良，开始借机竞拍房间，哎，一群蠢货。"} -{"prompt_audio":"voice_08.wav","emo_audio":"emo_hate.wav","emo_weight": 0.8, "emo_mode":1,"text":"你看看你，对我还有没有一点父子之间的信任了。"} -{"prompt_audio":"voice_09.wav","emo_vec_3":0.55,"emo_mode":2,"text":"对不起嘛！我的记性真的不太好，但是和你在一起的事情，我都会努力记住的~"} -{"prompt_audio":"voice_10.wav","emo_vec_7":0.45,"emo_mode":2,"text":"哇塞！这个爆率也太高了！欧皇附体了！"} +{"prompt_audio":"voice_07.wav","emo_audio":"emo_sad.wav","emo_weight": 1.0, "emo_mode":1,"text":"酒楼丧尽天良，开始借机竞拍房间，哎，一群蠢货。"} +{"prompt_audio":"voice_08.wav","emo_audio":"emo_hate.wav","emo_weight": 1.0, "emo_mode":1,"text":"你看看你，对我还有没有一点父子之间的信任了。"} +{"prompt_audio":"voice_09.wav","emo_vec_3":0.8,"emo_mode":2,"text":"对不起嘛！我的记性真的不太好，但是和你在一起的事情，我都会努力记住的~"} +{"prompt_audio":"voice_10.wav","emo_vec_7":1.0,"emo_mode":2,"text":"哇塞！这个爆率也太高了！欧皇附体了！"} {"prompt_audio":"voice_11.wav","emo_mode":3,"emo_text":"极度悲伤","text":"这些年的时光终究是错付了... "} {"prompt_audio":"voice_12.wav","emo_mode":3,"emo_text":"You scared me to death! What are you, a ghost?","text":"快躲起来！是他要来了！他要来抓我们了！"} \ No newline at end of file diff --git a/tools/i18n/locale/en_US.json b/tools/i18n/locale/en_US.json index abfbbe2..65e2858 100644 --- a/tools/i18n/locale/en_US.json +++ b/tools/i18n/locale/en_US.json @@ -42,7 +42,8 @@ "请上传情感参考音频": "Please upload the emotion reference audio", "当前模型版本": "Current model version: ", "请输入目标文本": "Please input the text to synthesize", - "例如：高兴，愤怒，悲伤等": "e.g., happy, angry, sad, etc.", + "例如：委屈巴巴、危险在悄悄逼近": "e.g. deeply sad, danger is creeping closer", "与音色参考音频相同": "Same as the voice reference", - "情感随机采样": "Randomize emotion sampling" + "情感随机采样": "Randomize emotion sampling", + "显示实验功能": "Show experimental features" } \ No newline at end of file diff --git a/tools/i18n/locale/zh_CN.json b/tools/i18n/locale/zh_CN.json index 9cdf5c4..15e76bf 100644 --- a/tools/i18n/locale/zh_CN.json +++ b/tools/i18n/locale/zh_CN.json @@ -38,5 +38,7 @@ "GPT2 采样设置": "GPT2 采样设置", "参数会影响音频多样性和生成速度详见": "参数会影响音频多样性和生成速度详见", "是否进行采样": "是否进行采样", - "生成Token最大数量，过小导致音频被截断": "生成Token最大数量，过小导致音频被截断" + "生成Token最大数量，过小导致音频被截断": "生成Token最大数量，过小导致音频被截断", + "显示实验功能": "显示实验功能", + "例如：委屈巴巴、危险在悄悄逼近": "例如：委屈巴巴、危险在悄悄逼近" } \ No newline at end of file diff --git a/webui.py b/webui.py index cf81a2b..f49c8af 100644 --- a/webui.py +++ b/webui.py @@ -6,6 +6,8 @@ import time import warnings +import numpy as np + warnings.filterwarnings("ignore", category=FutureWarning) warnings.filterwarnings("ignore", category=UserWarning) @@ -67,6 +69,9 @@ EMO_CHOICES = [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_BASE = EMO_CHOICES[:3] # 基础选项 +EMO_CHOICES_EXPERIMENTAL = EMO_CHOICES # 全部选项（包括文本描述） + os.makedirs("outputs/tasks",exist_ok=True) os.makedirs("prompts",exist_ok=True) @@ -95,9 +100,17 @@ with open("examples/cases.jsonl", "r", encoding="utf-8") as f: example.get("emo_vec_5",0), example.get("emo_vec_6",0), example.get("emo_vec_7",0), - example.get("emo_vec_8",0)] + example.get("emo_vec_8",0), + example.get("emo_text") is not None] ) +def normalize_emo_vec(emo_vec): + # emotion factors for better user experience + k_vec = [0.75,0.70,0.80,0.80,0.75,0.75,0.55,0.45] + tmp = np.array(k_vec) * np.array(emo_vec) + if np.sum(tmp) > 0.8: + tmp = tmp * 0.8/ np.sum(tmp) + return tmp.tolist() def gen_single(emo_control_method,prompt, text, emo_ref_path, emo_weight, @@ -128,15 +141,13 @@ def gen_single(emo_control_method,prompt, text, emo_control_method = emo_control_method.value if emo_control_method == 0: # emotion from speaker emo_ref_path = None # remove external reference audio - emo_weight = 1.0 if emo_control_method == 1: # emotion from reference audio - # emo_weight = emo_weight + # normalize emo_alpha for better user experience + emo_weight = emo_weight * 0.8 pass if emo_control_method == 2: # emotion from custom vectors vec = [vec1, vec2, vec3, vec4, vec5, vec6, vec7, vec8] - if sum(vec) > 1.5: - gr.Warning(i18n("情感向量之和不能超过1.5，请调整后重试。")) - return + vec = normalize_emo_vec(vec) else: # don't use the emotion vector inputs for the other modes vec = None @@ -182,13 +193,14 @@ with gr.Blocks(title="IndexTTS Demo") as demo: 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, + choices=EMO_CHOICES_BASE, type="index", - value=EMO_CHOICES[0],label=i18n("情感控制方式")) + value=EMO_CHOICES_BASE[0],label=i18n("情感控制方式")) # 情感参考音频部分 with gr.Group(visible=False) as emotion_reference_group: with gr.Row(): @@ -202,24 +214,28 @@ with gr.Blocks(title="IndexTTS Demo") as demo: 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=1.4, value=0.0, step=0.05) - vec2 = gr.Slider(label=i18n("怒"), minimum=0.0, maximum=1.4, value=0.0, step=0.05) - vec3 = gr.Slider(label=i18n("哀"), minimum=0.0, maximum=1.4, value=0.0, step=0.05) - vec4 = gr.Slider(label=i18n("惧"), minimum=0.0, maximum=1.4, value=0.0, step=0.05) + 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=1.4, value=0.0, step=0.05) - vec6 = gr.Slider(label=i18n("低落"), minimum=0.0, maximum=1.4, value=0.0, step=0.05) - vec7 = gr.Slider(label=i18n("惊喜"), minimum=0.0, maximum=1.4, value=0.0, step=0.05) - vec8 = gr.Slider(label=i18n("平静"), minimum=0.0, maximum=1.4, value=0.0, step=0.05) + 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: 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：高兴，愤怒，悲伤等")) + 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=1.6, value=0.8, step=0.01) + emo_weight = gr.Slider(label=i18n("情感权重"), minimum=0.0, maximum=1.0, value=0.8, step=0.01) - with gr.Accordion(i18n("高级生成参数设置"), open=False): + with gr.Accordion(i18n("高级生成参数设置"), open=False,visible=False) 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)._") @@ -257,8 +273,20 @@ with gr.Blocks(title="IndexTTS Demo") as demo: # typical_sampling, typical_mass, ] - if len(example_cases) > 0: - gr.Examples( + if len(example_cases) > 2: + example_table = gr.Examples( + examples=example_cases[:-2], + examples_per_page=20, + inputs=[prompt_audio, + emo_control_method, + input_text_single, + emo_upload, + emo_weight, + emo_text, + vec1,vec2,vec3,vec4,vec5,vec6,vec7,vec8,experimental_checkbox] + ) + elif len(example_cases) > 0: + example_table = gr.Examples( examples=example_cases, examples_per_page=20, inputs=[prompt_audio, @@ -267,7 +295,7 @@ with gr.Blocks(title="IndexTTS Demo") as demo: emo_upload, emo_weight, emo_text, - vec1,vec2,vec3,vec4,vec5,vec6,vec7,vec8] + vec1, vec2, vec3, vec4, vec5, vec6, vec7, vec8, experimental_checkbox] ) def on_input_text_change(text, max_text_tokens_per_segment): @@ -288,6 +316,7 @@ with gr.Blocks(title="IndexTTS Demo") as demo: return { segments_preview: gr.update(value=df), } + def on_method_select(emo_control_method): if emo_control_method == 1: # emotion reference audio return (gr.update(visible=True), @@ -301,7 +330,7 @@ with gr.Blocks(title="IndexTTS Demo") as demo: gr.update(visible=True), gr.update(visible=True), gr.update(visible=False), - gr.update(visible=True) + gr.update(visible=False) ) elif emo_control_method == 3: # emotion text description return (gr.update(visible=False), @@ -318,6 +347,14 @@ with gr.Blocks(title="IndexTTS Demo") as demo: gr.update(visible=False) ) + def on_experimental_change(is_exp): + # 切换情感控制选项 + # 第三个返回值实际没有起作用 + if is_exp: + return gr.update(choices=EMO_CHOICES_EXPERIMENTAL, value=EMO_CHOICES_EXPERIMENTAL[0]), gr.update(visible=True),gr.update(value=example_cases) + else: + return gr.update(choices=EMO_CHOICES_BASE, value=EMO_CHOICES_BASE[0]), gr.update(visible=False),gr.update(value=example_cases[:-2]) + emo_control_method.select(on_method_select, inputs=[emo_control_method], outputs=[emotion_reference_group, @@ -332,11 +369,19 @@ with gr.Blocks(title="IndexTTS Demo") as demo: inputs=[input_text_single, max_text_tokens_per_segment], outputs=[segments_preview] ) + + experimental_checkbox.change( + on_experimental_change, + inputs=[experimental_checkbox], + outputs=[emo_control_method, advanced_settings_group,example_table.dataset] # 高级参数Accordion + ) + 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])