Update ui/components.py

ui/components.py

@@ -1,8 +1,6 @@
 """
 ACE-Step: A Step Towards Music Generation Foundation Model
-
 https://github.com/ace-step/ACE-Step
-
 Apache 2.0 License
 """
 
@@ -17,31 +15,26 @@ Neon lights they flicker bright
 City hums in dead of night
 Rhythms pulse through concrete veins
 Lost in echoes of refrains
-
 [verse]
 Bassline groovin' in my chest
 Heartbeats match the city's zest
 Electric whispers fill the air
 Synthesized dreams everywhere
-
 [chorus]
 Turn it up and let it flow
 Feel the fire let it grow
 In this rhythm we belong
 Hear the night sing out our song
-
 [verse]
 Guitar strings they start to weep
 Wake the soul from silent sleep
 Every note a story told
 In this night we’re bold and gold
-
 [bridge]
 Voices blend in harmony
 Lost in pure cacophony
 Timeless echoes timeless cries
 Soulful shouts beneath the skies
-
 [verse]
 Keyboard dances on the keys
 Melodies on evening breeze
@@ -51,31 +44,31 @@ In this moment we take flight
 
 # First, let's define the presets at the top of the file, after the imports
 GENRE_PRESETS = {
-    "Modern Pop": "pop, synth, drums, guitar, 120 bpm, upbeat, catchy, vibrant, female vocals, polished vocals",
-    "Rock": "rock, electric guitar, drums, bass, 130 bpm, energetic, rebellious, gritty, male vocals, raw vocals",
-    "Hip Hop": "hip hop, 808 bass, hi-hats, synth, 90 bpm, bold, urban, intense, male vocals, rhythmic vocals",
-    "Country": "country, acoustic guitar, steel guitar, fiddle, 100 bpm, heartfelt, rustic, warm, male vocals, twangy vocals",
-    "EDM": "edm, synth, bass, kick drum, 128 bpm, euphoric, pulsating, energetic, instrumental",
-    "Reggae": "reggae, guitar, bass, drums, 80 bpm, chill, soulful, positive, male vocals, smooth vocals",
-    "Classical": "classical, orchestral, strings, piano, 60 bpm, elegant, emotive, timeless, instrumental",
-    "Jazz": "jazz, saxophone, piano, double bass, 110 bpm, smooth, improvisational, soulful, male vocals, crooning vocals",
-    "Metal": "metal, electric guitar, double kick drum, bass, 160 bpm, aggressive, intense, heavy, male vocals, screamed vocals",
-    "R&B": "r&b, synth, bass, drums, 85 bpm, sultry, groovy, romantic, female vocals, silky vocals"
+    "现代流行 (Modern Pop)": "pop, synth, drums, guitar, 120 bpm, upbeat, catchy, vibrant, female vocals, polished vocals",
+    "摇滚 (Rock)": "rock, electric guitar, drums, bass, 130 bpm, energetic, rebellious, gritty, male vocals, raw vocals",
+    "嘻哈 (Hip Hop)": "hip hop, 808 bass, hi-hats, synth, 90 bpm, bold, urban, intense, male vocals, rhythmic vocals",
+    "乡村 (Country)": "country, acoustic guitar, steel guitar, fiddle, 100 bpm, heartfelt, rustic, warm, male vocals, twangy vocals",
+    "电子舞曲 (EDM)": "edm, synth, bass, kick drum, 128 bpm, euphoric, pulsating, energetic, instrumental",
+    "雷鬼 (Reggae)": "reggae, guitar, bass, drums, 80 bpm, chill, soulful, positive, male vocals, smooth vocals",
+    "古典 (Classical)": "classical, orchestral, strings, piano, 60 bpm, elegant, emotive, timeless, instrumental",
+    "爵士 (Jazz)": "jazz, saxophone, piano, double bass, 110 bpm, smooth, improvisational, soulful, male vocals, crooning vocals",
+    "金属 (Metal)": "metal, electric guitar, double kick drum, bass, 160 bpm, aggressive, intense, heavy, male vocals, screamed vocals",
+    "R&B (R&B)": "r&b, synth, bass, drums, 85 bpm, sultry, groovy, romantic, female vocals, silky vocals"
 }
 
 # Add this function to handle preset selection
 def update_tags_from_preset(preset_name):
-    if preset_name == "Custom":
+    if preset_name == "自定义 (Custom)":
         return ""
     return GENRE_PRESETS.get(preset_name, "")
 
 
-def create_output_ui(task_name="Text2Music"):
+def create_output_ui(task_name="文本转音乐"):
     # For many consumer-grade GPU devices, only one batch can be run
-    output_audio1 = gr.Audio(type="filepath", label=f"{task_name} Generated Audio 1")
+    output_audio1 = gr.Audio(type="filepath", label=f"{task_name} 生成的音频 1")
     # output_audio2 = gr.Audio(type="filepath", label="Generated Audio 2")
-    with gr.Accordion(f"{task_name} Parameters", open=False):
-        input_params_json = gr.JSON(label=f"{task_name} Parameters")
+    with gr.Accordion(f"{task_name} 参数", open=False):
+        input_params_json = gr.JSON(label=f"{task_name} 参数")
     # outputs = [output_audio1, output_audio2]
     outputs = [output_audio1]
     return outputs, input_params_json
@@ -102,26 +95,26 @@ def create_text2music_ui(
                     240.0,
                     step=0.00001,
                     value=-1,
-                    label="Audio Duration",
+                    label="音频时长",
                     interactive=True,
-                    info="-1 means random duration (30 ~ 240).",
+                    info="-1 表示随机时长 (30 ~ 240秒)。",
                     scale=9,
                 )
-                sample_bnt = gr.Button("Sample", variant="secondary", scale=1)
+                sample_bnt = gr.Button("示例", variant="secondary", scale=1)
 
             # audio2audio
             with gr.Row(equal_height=True):
-                audio2audio_enable = gr.Checkbox(label="Enable Audio2Audio", value=False, info="Check to enable Audio-to-Audio generation using a reference audio.", elem_id="audio2audio_checkbox")
+                audio2audio_enable = gr.Checkbox(label="启用音频到音频生成", value=False, info="勾选以使用参考音频进行音频到音频生成。", elem_id="audio2audio_checkbox")
                 lora_name_or_path = gr.Dropdown(
-                    label="Lora Name or Path",
+                    label="Lora 模型名称或路径",
                     choices=["ACE-Step/ACE-Step-v1-chinese-rap-LoRA", "none"],
                     value="none",
                     allow_custom_value=True,
                 )
 
-            ref_audio_input = gr.Audio(type="filepath", label="Reference Audio (for Audio2Audio)", visible=False, elem_id="ref_audio_input", show_download_button=True)
+            ref_audio_input = gr.Audio(type="filepath", label="参考音频 (用于音频到音频生成)", visible=False, elem_id="ref_audio_input", show_download_button=True)
             ref_audio_strength = gr.Slider(
-                label="Refer audio strength",
+                label="参考音频强度",
                 minimum=0.0,
                 maximum=1.0,
                 step=0.01,
@@ -145,17 +138,17 @@ def create_text2music_ui(
 
             with gr.Column(scale=2):
                 with gr.Group():
-                    gr.Markdown("""<center>Support tags, descriptions, and scene. Use commas to separate different tags.<br>Tags and lyrics examples are from AI music generation community.</center>""")
+                    gr.Markdown("""<center>支持标签、描述和场景。使用逗号分隔不同的标签。<br>标签和歌词示例来自AI音乐生成社区。</center>""")
                     with gr.Row():
                         genre_preset = gr.Dropdown(
-                            choices=["Custom"] + list(GENRE_PRESETS.keys()),
-                            value="Custom",
-                            label="Preset",
+                            choices=["自定义 (Custom)"] + list(GENRE_PRESETS.keys()),
+                            value="自定义 (Custom)",
+                            label="预设",
                             scale=1,
                         )
                         prompt = gr.Textbox(
                             lines=1,
-                            label="Tags",
+                            label="标签",
                             max_lines=4,
                             value=TAG_DEFAULT,
                             scale=9,
@@ -168,21 +161,21 @@ def create_text2music_ui(
                 outputs=[prompt]
             )
             with gr.Group():
-                gr.Markdown("""<center>Support lyric structure tags like [verse], [chorus], and [bridge] to separate different parts of the lyrics.<br>Use [instrumental] or [inst] to generate instrumental music. Not support genre structure tag in lyrics</center>""")
+                gr.Markdown("""<center>支持歌词结构标签，如 [verse]、[chorus] 和 [bridge] 来分隔歌词的不同部分。<br>使用 [instrumental] 或 [inst] 生成纯音乐。不支持歌词中的流派结构标签。</center>""")
                 lyrics = gr.Textbox(
                     lines=9,
-                    label="Lyrics",
+                    label="歌词",
                     max_lines=13,
                     value=LYRIC_DEFAULT,
                 )
 
-            with gr.Accordion("Basic Settings", open=False):
+            with gr.Accordion("基本设置", open=False):
                 infer_step = gr.Slider(
                     minimum=1,
                     maximum=200,
                     step=1,
                     value=60,
-                    label="Infer Steps",
+                    label="推理步数",
                     interactive=True,
                 )
                 guidance_scale = gr.Slider(
@@ -190,64 +183,64 @@ def create_text2music_ui(
                     maximum=30.0,
                     step=0.1,
                     value=15.0,
-                    label="Guidance Scale",
+                    label="引导尺度",
                     interactive=True,
-                    info="When guidance_scale_lyric > 1 and guidance_scale_text > 1, the guidance scale will not be applied.",
+                    info="当 guidance_scale_lyric > 1 且 guidance_scale_text > 1 时，不应用引导尺度。",
                 )
                 guidance_scale_text = gr.Slider(
                     minimum=0.0,
                     maximum=10.0,
                     step=0.1,
                     value=0.0,
-                    label="Guidance Scale Text",
+                    label="文本引导尺度",
                     interactive=True,
-                    info="Guidance scale for text condition. It can only apply to cfg. set guidance_scale_text=5.0, guidance_scale_lyric=1.5 for start",
+                    info="文本条件的引导尺度。仅适用于 cfg。建议设置 guidance_scale_text=5.0, guidance_scale_lyric=1.5 作为开始。",
                 )
                 guidance_scale_lyric = gr.Slider(
                     minimum=0.0,
                     maximum=10.0,
                     step=0.1,
                     value=0.0,
-                    label="Guidance Scale Lyric",
+                    label="歌词引导尺度",
                     interactive=True,
                 )
 
                 manual_seeds = gr.Textbox(
-                    label="manual seeds (default None)",
+                    label="手动种子 (默认为无)",
                     placeholder="1,2,3,4",
                     value=None,
-                    info="Seed for the generation",
+                    info="生成种子",
                 )
 
-            with gr.Accordion("Advanced Settings", open=False):
+            with gr.Accordion("高级设置", open=False):
                 scheduler_type = gr.Radio(
                     ["euler", "heun"],
                     value="euler",
-                    label="Scheduler Type",
+                    label="调度器类型",
                     elem_id="scheduler_type",
-                    info="Scheduler type for the generation. euler is recommended. heun will take more time.",
+                    info="生成调度器类型。推荐使用 euler。heun 将花费更多时间。",
                 )
                 cfg_type = gr.Radio(
                     ["cfg", "apg", "cfg_star"],
                     value="apg",
-                    label="CFG Type",
+                    label="CFG 类型",
                     elem_id="cfg_type",
-                    info="CFG type for the generation. apg is recommended. cfg and cfg_star are almost the same.",
+                    info="生成 CFG 类型。推荐使用 apg。cfg 和 cfg_star 几乎相同。",
                 )
                 use_erg_tag = gr.Checkbox(
-                    label="use ERG for tag",
+                    label="对标签使用 ERG",
                     value=True,
-                    info="Use Entropy Rectifying Guidance for tag. It will multiple a temperature to the attention to make a weaker tag condition and make better diversity.",
+                    info="对标签使用熵校正引导。它将注意力乘以一个温度，以减弱标签条件并提高多样性。",
                 )
                 use_erg_lyric = gr.Checkbox(
-                    label="use ERG for lyric",
+                    label="对歌词使用 ERG",
                     value=False,
-                    info="The same but apply to lyric encoder's attention.",
+                    info="同上，但应用于歌词编码器的注意力。",
                 )
                 use_erg_diffusion = gr.Checkbox(
-                    label="use ERG for diffusion",
+                    label="对扩散模型使用 ERG",
                     value=True,
-                    info="The same but apply to diffusion model's attention.",
+                    info="同上，但应用于扩散模型的注意力。",
                 )
 
                 omega_scale = gr.Slider(
@@ -255,9 +248,9 @@ def create_text2music_ui(
                     maximum=100.0,
                     step=0.1,
                     value=10.0,
-                    label="Granularity Scale",
+                    label="粒度尺度",
                     interactive=True,
-                    info="Granularity scale for the generation. Higher values can reduce artifacts",
+                    info="生成粒度尺度。值越高可以减少伪影。",
                 )
 
                 guidance_interval = gr.Slider(
@@ -265,48 +258,48 @@ def create_text2music_ui(
                     maximum=1.0,
                     step=0.01,
                     value=0.5,
-                    label="Guidance Interval",
+                    label="引导间隔",
                     interactive=True,
-                    info="Guidance interval for the generation. 0.5 means only apply guidance in the middle steps (0.25 * infer_steps to 0.75 * infer_steps)",
+                    info="生成引导间隔。0.5 表示仅在中间步骤应用引导 (0.25 * 推理步数 到 0.75 * 推理步数)。",
                 )
                 guidance_interval_decay = gr.Slider(
                     minimum=0.0,
                     maximum=1.0,
                     step=0.01,
                     value=0.0,
-                    label="Guidance Interval Decay",
+                    label="引导间隔衰减",
                     interactive=True,
-                    info="Guidance interval decay for the generation. Guidance scale will decay from guidance_scale to min_guidance_scale in the interval. 0.0 means no decay.",
+                    info="生成引导间隔衰减。引导尺度将在此间隔内从 guidance_scale 衰减到 min_guidance_scale。0.0 表示不衰减。",
                 )
                 min_guidance_scale = gr.Slider(
                     minimum=0.0,
                     maximum=200.0,
                     step=0.1,
                     value=3.0,
-                    label="Min Guidance Scale",
+                    label="最小引导尺度",
                     interactive=True,
-                    info="Min guidance scale for guidance interval decay's end scale",
+                    info="引导间隔衰减结束时的最小引导尺度。",
                 )
                 oss_steps = gr.Textbox(
-                    label="OSS Steps",
+                    label="OSS 步数",
                     placeholder="16, 29, 52, 96, 129, 158, 172, 183, 189, 200",
                     value=None,
-                    info="Optimal Steps for the generation. But not test well",
+                    info="生成的最优步数。但未充分测试。",
                 )
 
-            text2music_bnt = gr.Button("Generate", variant="primary")
+            text2music_bnt = gr.Button("生成", variant="primary")
 
         with gr.Column():
             outputs, input_params_json = create_output_ui()
-            with gr.Tab("retake"):
+            with gr.Tab("重试"):
                 retake_variance = gr.Slider(
-                    minimum=0.0, maximum=1.0, step=0.01, value=0.2, label="variance"
+                    minimum=0.0, maximum=1.0, step=0.01, value=0.2, label="方差"
                 )
                 retake_seeds = gr.Textbox(
-                    label="retake seeds (default None)", placeholder="", value=None
+                    label="重试种子 (默认为无)", placeholder="", value=None
                 )
-                retake_bnt = gr.Button("Retake", variant="primary")
-                retake_outputs, retake_input_params_json = create_output_ui("Retake")
+                retake_bnt = gr.Button("重试", variant="primary")
+                retake_outputs, retake_input_params_json = create_output_ui("重试")
 
                 def retake_process_func(json_data, retake_variance, retake_seeds):
                     return text2music_process_func(
@@ -351,19 +344,19 @@ def create_text2music_ui(
                     ],
                     outputs=retake_outputs + [retake_input_params_json],
                 )
-            with gr.Tab("repainting"):
+            with gr.Tab("重绘"):
                 retake_variance = gr.Slider(
-                    minimum=0.0, maximum=1.0, step=0.01, value=0.2, label="variance"
+                    minimum=0.0, maximum=1.0, step=0.01, value=0.2, label="方差"
                 )
                 retake_seeds = gr.Textbox(
-                    label="repaint seeds (default None)", placeholder="", value=None
+                    label="重绘种子 (默认为无)", placeholder="", value=None
                 )
                 repaint_start = gr.Slider(
                     minimum=0.0,
                     maximum=240.0,
                     step=0.01,
                     value=0.0,
-                    label="Repaint Start Time",
+                    label="重绘开始时间",
                     interactive=True,
                 )
                 repaint_end = gr.Slider(
@@ -371,18 +364,18 @@ def create_text2music_ui(
                     maximum=240.0,
                     step=0.01,
                     value=30.0,
-                    label="Repaint End Time",
+                    label="重绘结束时间",
                     interactive=True,
                 )
                 repaint_source = gr.Radio(
-                    ["text2music", "last_repaint", "upload"],
-                    value="text2music",
-                    label="Repaint Source",
+                    ["文本转音乐", "上次重绘", "上传"],
+                    value="文本转音乐",
+                    label="重绘来源",
                     elem_id="repaint_source",
                 )
 
                 repaint_source_audio_upload = gr.Audio(
-                    label="Upload Audio",
+                    label="上传音频",
                     type="filepath",
                     visible=False,
                     elem_id="repaint_source_audio_upload",
@@ -390,14 +383,14 @@ def create_text2music_ui(
                 )
                 repaint_source.change(
                     fn=lambda x: gr.update(
-                        visible=x == "upload", elem_id="repaint_source_audio_upload"
+                        visible=x == "上传", elem_id="repaint_source_audio_upload"
                     ),
                     inputs=[repaint_source],
                     outputs=[repaint_source_audio_upload],
                 )
 
-                repaint_bnt = gr.Button("Repaint", variant="primary")
-                repaint_outputs, repaint_input_params_json = create_output_ui("Repaint")
+                repaint_bnt = gr.Button("重绘", variant="primary")
+                repaint_outputs, repaint_input_params_json = create_output_ui("重绘")
 
                 def repaint_process_func(
                     text2music_json_data,
@@ -426,14 +419,14 @@ def create_text2music_ui(
                     guidance_scale_text,
                     guidance_scale_lyric,
                 ):
-                    if repaint_source == "upload":
+                    if repaint_source == "上传":
                         src_audio_path = repaint_source_audio_upload
                         audio_duration = librosa.get_duration(filename=src_audio_path)
                         json_data = {"audio_duration": audio_duration}
-                    elif repaint_source == "text2music":
+                    elif repaint_source == "文本转音乐":
                         json_data = text2music_json_data
                         src_audio_path = json_data["audio_path"]
-                    elif repaint_source == "last_repaint":
+                    elif repaint_source == "上次重绘":
                         json_data = repaint_json_data
                         src_audio_path = json_data["audio_path"]
 
@@ -496,26 +489,26 @@ def create_text2music_ui(
                     ],
                     outputs=repaint_outputs + [repaint_input_params_json],
                 )
-            with gr.Tab("edit"):
-                edit_prompt = gr.Textbox(lines=2, label="Edit Tags", max_lines=4)
-                edit_lyrics = gr.Textbox(lines=9, label="Edit Lyrics", max_lines=13)
+            with gr.Tab("编辑"):
+                edit_prompt = gr.Textbox(lines=2, label="编辑标签", max_lines=4)
+                edit_lyrics = gr.Textbox(lines=9, label="编辑歌词", max_lines=13)
                 retake_seeds = gr.Textbox(
-                    label="edit seeds (default None)", placeholder="", value=None
+                    label="编辑种子 (默认为无)", placeholder="", value=None
                 )
 
                 edit_type = gr.Radio(
-                    ["only_lyrics", "remix"],
-                    value="only_lyrics",
-                    label="Edit Type",
+                    ["仅歌词", "混音"],
+                    value="仅歌词",
+                    label="编辑类型",
                     elem_id="edit_type",
-                    info="`only_lyrics` will keep the whole song the same except lyrics difference. Make your diffrence smaller, e.g. one lyrc line change.\nremix can change the song melody and genre",
+                    info="`仅歌词` 将保持整首歌相同，除了歌词差异。使您的差异更小，例如更改一行歌词。\n`混音` 可以改变歌曲的旋律和流派。",
                 )
                 edit_n_min = gr.Slider(
                     minimum=0.0,
                     maximum=1.0,
                     step=0.01,
                     value=0.6,
-                    label="edit_n_min",
+                    label="编辑 n_min",
                     interactive=True,
                 )
                 edit_n_max = gr.Slider(
@@ -523,15 +516,15 @@ def create_text2music_ui(
                     maximum=1.0,
                     step=0.01,
                     value=1.0,
-                    label="edit_n_max",
+                    label="编辑 n_max",
                     interactive=True,
                 )
 
                 def edit_type_change_func(edit_type):
-                    if edit_type == "only_lyrics":
+                    if edit_type == "仅歌词":
                         n_min = 0.6
                         n_max = 1.0
-                    elif edit_type == "remix":
+                    elif edit_type == "混音":
                         n_min = 0.2
                         n_max = 0.4
                     return n_min, n_max
@@ -543,13 +536,13 @@ def create_text2music_ui(
                 )
 
                 edit_source = gr.Radio(
-                    ["text2music", "last_edit", "upload"],
-                    value="text2music",
-                    label="Edit Source",
+                    ["文本转音乐", "上次编辑", "上传"],
+                    value="文本转音乐",
+                    label="编辑来源",
                     elem_id="edit_source",
                 )
                 edit_source_audio_upload = gr.Audio(
-                    label="Upload Audio",
+                    label="上传音频",
                     type="filepath",
                     visible=False,
                     elem_id="edit_source_audio_upload",
@@ -557,14 +550,14 @@ def create_text2music_ui(
                 )
                 edit_source.change(
                     fn=lambda x: gr.update(
-                        visible=x == "upload", elem_id="edit_source_audio_upload"
+                        visible=x == "上传", elem_id="edit_source_audio_upload"
                     ),
                     inputs=[edit_source],
                     outputs=[edit_source_audio_upload],
                 )
 
-                edit_bnt = gr.Button("Edit", variant="primary")
-                edit_outputs, edit_input_params_json = create_output_ui("Edit")
+                edit_bnt = gr.Button("编辑", variant="primary")
+                edit_outputs, edit_input_params_json = create_output_ui("编辑")
 
                 def edit_process_func(
                     text2music_json_data,
@@ -594,14 +587,14 @@ def create_text2music_ui(
                     guidance_scale_lyric,
                     retake_seeds,
                 ):
-                    if edit_source == "upload":
+                    if edit_source == "上传":
                         src_audio_path = edit_source_audio_upload
                         audio_duration = librosa.get_duration(filename=src_audio_path)
                         json_data = {"audio_duration": audio_duration}
-                    elif edit_source == "text2music":
+                    elif edit_source == "文本转音乐":
                         json_data = text2music_json_data
                         src_audio_path = json_data["audio_path"]
-                    elif edit_source == "last_edit":
+                    elif edit_source == "上次编辑":
                         json_data = edit_input_params_json
                         src_audio_path = json_data["audio_path"]
 
@@ -671,16 +664,16 @@ def create_text2music_ui(
                     ],
                     outputs=edit_outputs + [edit_input_params_json],
                 )
-            with gr.Tab("extend"):
+            with gr.Tab("扩展"):
                 extend_seeds = gr.Textbox(
-                    label="extend seeds (default None)", placeholder="", value=None
+                    label="扩展种子 (默认为无)", placeholder="", value=None
                 )
                 left_extend_length = gr.Slider(
                     minimum=0.0,
                     maximum=240.0,
                     step=0.01,
                     value=0.0,
-                    label="Left Extend Length",
+                    label="左侧扩展长度",
                     interactive=True,
                 )
                 right_extend_length = gr.Slider(
@@ -688,18 +681,18 @@ def create_text2music_ui(
                     maximum=240.0,
                     step=0.01,
                     value=30.0,
-                    label="Right Extend Length",
+                    label="右侧扩展长度",
                     interactive=True,
                 )
                 extend_source = gr.Radio(
-                    ["text2music", "last_extend", "upload"],
-                    value="text2music",
-                    label="Extend Source",
+                    ["文本转音乐", "上次扩展", "上传"],
+                    value="文本转音乐",
+                    label="扩展来源",
                     elem_id="extend_source",
                 )
 
                 extend_source_audio_upload = gr.Audio(
-                    label="Upload Audio",
+                    label="上传音频",
                     type="filepath",
                     visible=False,
                     elem_id="extend_source_audio_upload",
@@ -707,14 +700,14 @@ def create_text2music_ui(
                 )
                 extend_source.change(
                     fn=lambda x: gr.update(
-                        visible=x == "upload", elem_id="extend_source_audio_upload"
+                        visible=x == "上传", elem_id="extend_source_audio_upload"
                     ),
                     inputs=[extend_source],
                     outputs=[extend_source_audio_upload],
                 )
 
-                extend_bnt = gr.Button("Extend", variant="primary")
-                extend_outputs, extend_input_params_json = create_output_ui("Extend")
+                extend_bnt = gr.Button("扩展", variant="primary")
+                extend_outputs, extend_input_params_json = create_output_ui("扩展")
 
                 def extend_process_func(
                     text2music_json_data,
@@ -742,15 +735,15 @@ def create_text2music_ui(
                     guidance_scale_text,
                     guidance_scale_lyric,
                 ):
-                    if extend_source == "upload":
+                    if extend_source == "上传":
                         src_audio_path = extend_source_audio_upload
                         # get audio duration
                         audio_duration = librosa.get_duration(filename=src_audio_path)
                         json_data = {"audio_duration": audio_duration}
-                    elif extend_source == "text2music":
+                    elif extend_source == "文本转音乐":
                         json_data = text2music_json_data
                         src_audio_path = json_data["audio_path"]
-                    elif extend_source == "last_extend":
+                    elif extend_source == "上次扩展":
                         json_data = extend_input_params_json
                         src_audio_path = json_data["audio_path"]
 
@@ -928,19 +921,9 @@ def create_main_demo_ui(
     load_data_func=dump_func,
 ):
     with gr.Blocks(
-        title="ACE-Step Model 1.0 DEMO",
+        title="ACE-Step 模型 1.0 演示",
     ) as demo:
-        gr.Markdown(
-            """
-            <h1 style="text-align: center;">ACE-Step: A Step Towards Music Generation Foundation Model</h1>
-            <p>
-                <a href="https://ace-step.github.io/" target='_blank'>Project</a> |
-                <a href="https://huggingface.co/ACE-Step/ACE-Step-v1-3.5B">Checkpoints</a> |
-                <a href="https://discord.gg/rjAZz2xBdG" target='_blank'>Discord</a> 
-            </p>
-        """
-        )
-        with gr.Tab("text2music"):
+        with gr.Tab("文本转音乐"):
             create_text2music_ui(
                 gr=gr,
                 text2music_process_func=text2music_process_func,
@@ -955,4 +938,4 @@ if __name__ == "__main__":
     demo.launch(
         server_name="0.0.0.0",
         server_port=7860,
-    )
+    )