diff --git a/examples/cases.jsonl b/examples/cases.jsonl index 98b5f30..69eee3e 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": 0.65, "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": 0.65, "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_07.wav","emo_audio":"emo_sad.wav","emo_weight":0.65,"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":0.65,"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_weight": 0.8,"emo_mode":2,"emo_vec_3":0.8,"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_weight": 0.8,"emo_mode":2,"emo_vec_7":1.0,"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 65e2858..e072dc1 100644 --- a/tools/i18n/locale/en_US.json +++ b/tools/i18n/locale/en_US.json @@ -42,8 +42,9 @@ "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：委屈巴巴、危险在悄悄逼近": "e.g. deeply sad, danger is creeping closer", + "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", - "显示实验功能": "Show experimental features" + "显示实验功能": "Show experimental features", + "提示：此功能为实验版，结果尚不稳定，我们正在持续优化中。": "Note: This feature is currently experimental and may not produce satisfactory results. We're dedicated to improving its performance in a future release." } \ No newline at end of file diff --git a/tools/i18n/locale/zh_CN.json b/tools/i18n/locale/zh_CN.json index 15e76bf..ca4045c 100644 --- a/tools/i18n/locale/zh_CN.json +++ b/tools/i18n/locale/zh_CN.json @@ -39,6 +39,9 @@ "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", + "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", + "与音色参考音频相同": "与音色参考音频相同", + "情感随机采样": "情感随机采样", "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" + "提示：此功能为实验版，结果尚不稳定，我们正在持续优化中。": "提示：此功能为实验版，结果尚不稳定，我们正在持续优化中。" } \ No newline at end of file diff --git a/webui.py b/webui.py index 9006fae..9c674a0 100644 --- a/webui.py +++ b/webui.py @@ -1,3 +1,4 @@ +import html import json import os import sys @@ -63,19 +64,18 @@ LANGUAGES = { "中文": "zh_CN", "English": "en_US" } -EMO_CHOICES = [i18n("与音色参考音频相同"), +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_BASE = EMO_CHOICES[:3] # 基础选项 -EMO_CHOICES_EXPERIMENTAL = EMO_CHOICES # 全部选项（包括文本描述） +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: - example_cases = [] for line in f: line = line.strip() if not line: @@ -85,8 +85,9 @@ with open("examples/cases.jsonl", "r", encoding="utf-8") as f: 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[example.get("emo_mode",0)], + EMO_CHOICES_ALL[example.get("emo_mode",0)], example.get("text"), emo_audio_path, example.get("emo_weight",1.0), @@ -99,8 +100,14 @@ with open("examples/cases.jsonl", "r", encoding="utf-8") as f: example.get("emo_vec_6",0), example.get("emo_vec_7",0), example.get("emo_vec_8",0), - example.get("emo_text") is not None] - ) + ]) + +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, @@ -159,6 +166,12 @@ def update_prompt_audio(): update_button = gr.update(interactive=True) return update_button +def create_warning_message(warning_text): + return gr.HTML(f"
{html.escape(warning_text)}
") + +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(''' @@ -181,14 +194,24 @@ 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) + + 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_BASE, + choices=EMO_CHOICES_OFFICIAL, type="index", - value=EMO_CHOICES_BASE[0],label=i18n("情感控制方式")) + 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(): @@ -213,13 +236,13 @@ with gr.Blocks(title="IndexTTS Demo") as demo: 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) @@ -261,23 +284,55 @@ with gr.Blocks(title="IndexTTS Demo") as demo: # typical_sampling, typical_mass, ] - if len(example_cases) > 0: - example_table = gr.Examples( - examples=( - example_cases[:-2] - if len(example_cases) > 2 - else example_cases - ), - examples_per_page=20, - inputs=[prompt_audio, - emo_control_method, + # 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, - experimental_checkbox] - ) + 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: @@ -328,14 +383,6 @@ 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(value=example_cases) - else: - return gr.update(choices=EMO_CHOICES_BASE, value=EMO_CHOICES_BASE[0]), gr.update(value=example_cases[:-2]) - emo_control_method.change(on_method_change, inputs=[emo_control_method], outputs=[emotion_reference_group, @@ -345,18 +392,30 @@ with gr.Blocks(title="IndexTTS Demo") as demo: 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] ) - experimental_checkbox.change( - on_experimental_change, - inputs=[experimental_checkbox], - outputs=[emo_control_method, 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],