init

.idea/workspace.xml

@@ -2,7 +2,7 @@
 <project version="4">
   <component name="ChangeListManager">
     <list default="true" id="6f3a79aa-e3bd-440d-b0d9-38be2ab06fa3" name="Changes" comment="init">
-      <change beforePath="$PROJECT_DIR$/README.md" beforeDir="false" />
+      <change afterPath="$PROJECT_DIR$/app.py" afterDir="false" />
     </list>
     <option name="SHOW_DIALOG" value="false" />
     <option name="HIGHLIGHT_CONFLICTS" value="true" />
@@ -41,7 +41,77 @@
       <option name="project" value="LOCAL" />
       <updated>1683456502470</updated>
     </task>
-    <option name="localTasksCounter" value="2" />
+    <task id="LOCAL-00002" summary="init">
+      <created>1683456698781</created>
+      <option name="number" value="00002" />
+      <option name="presentableId" value="LOCAL-00002" />
+      <option name="project" value="LOCAL" />
+      <updated>1683456698781</updated>
+    </task>
+    <task id="LOCAL-00003" summary="init">
+      <created>1683456708549</created>
+      <option name="number" value="00003" />
+      <option name="presentableId" value="LOCAL-00003" />
+      <option name="project" value="LOCAL" />
+      <updated>1683456708549</updated>
+    </task>
+    <task id="LOCAL-00004" summary="init">
+      <created>1683456749208</created>
+      <option name="number" value="00004" />
+      <option name="presentableId" value="LOCAL-00004" />
+      <option name="project" value="LOCAL" />
+      <updated>1683456749208</updated>
+    </task>
+    <task id="LOCAL-00005" summary="init">
+      <created>1683456785738</created>
+      <option name="number" value="00005" />
+      <option name="presentableId" value="LOCAL-00005" />
+      <option name="project" value="LOCAL" />
+      <updated>1683456785738</updated>
+    </task>
+    <task id="LOCAL-00006" summary="init">
+      <created>1683456838521</created>
+      <option name="number" value="00006" />
+      <option name="presentableId" value="LOCAL-00006" />
+      <option name="project" value="LOCAL" />
+      <updated>1683456838521</updated>
+    </task>
+    <task id="LOCAL-00007" summary="init">
+      <created>1683456856631</created>
+      <option name="number" value="00007" />
+      <option name="presentableId" value="LOCAL-00007" />
+      <option name="project" value="LOCAL" />
+      <updated>1683456856631</updated>
+    </task>
+    <task id="LOCAL-00008" summary="init">
+      <created>1683456878691</created>
+      <option name="number" value="00008" />
+      <option name="presentableId" value="LOCAL-00008" />
+      <option name="project" value="LOCAL" />
+      <updated>1683456878691</updated>
+    </task>
+    <task id="LOCAL-00009" summary="init">
+      <created>1683456940183</created>
+      <option name="number" value="00009" />
+      <option name="presentableId" value="LOCAL-00009" />
+      <option name="project" value="LOCAL" />
+      <updated>1683456940183</updated>
+    </task>
+    <task id="LOCAL-00010" summary="init">
+      <created>1683456950180</created>
+      <option name="number" value="00010" />
+      <option name="presentableId" value="LOCAL-00010" />
+      <option name="project" value="LOCAL" />
+      <updated>1683456950180</updated>
+    </task>
+    <task id="LOCAL-00011" summary="init">
+      <created>1683456957352</created>
+      <option name="number" value="00011" />
+      <option name="presentableId" value="LOCAL-00011" />
+      <option name="project" value="LOCAL" />
+      <updated>1683456957352</updated>
+    </task>
+    <option name="localTasksCounter" value="12" />
     <servers />
   </component>
   <component name="Vcs.Log.Tabs.Properties">

app.py

@@ -0,0 +1,213 @@
+Hugging Face's logo
+Hugging Face
+Search models, datasets, users...
+Models
+Datasets
+Spaces
+Docs
+Solutions
+Pricing
+
+
+
+Spaces:
+
+suno
+/
+bark Copied
+like
+758
+App
+Files
+Community
+54
+bark
+/
+app.py
+georg-suno's picture
+georg-suno
+fix-header-button (#11)
+589dfd0
+11 days ago
+raw
+history
+blame
+contribute
+delete
+8.24 kB
+import numpy as np
+import gradio as gr
+from bark import SAMPLE_RATE, generate_audio, preload_models
+from bark.generation import SUPPORTED_LANGS
+from share_btn import community_icon_html, loading_icon_html, share_js
+
+DEBUG_MODE = False
+
+if not DEBUG_MODE:
+    _ = preload_models()
+
+AVAILABLE_PROMPTS = ["Unconditional", "Announcer"]
+PROMPT_LOOKUP = {}
+for _, lang in SUPPORTED_LANGS:
+    for n in range(10):
+        label = f"Speaker {n} ({lang})"
+        AVAILABLE_PROMPTS.append(label)
+        PROMPT_LOOKUP[label] = f"{lang}_speaker_{n}"
+PROMPT_LOOKUP["Unconditional"] = None
+PROMPT_LOOKUP["Announcer"] = "announcer"
+
+default_text = "Hello, my name is Suno. And, uh — and I like pizza. [laughs]\nBut I also have other interests such as playing tic tac toe."
+
+title = "# 🐶 Bark</div>"
+
+description = """
+<div>
+<a style="display:inline-block" href='https://github.com/suno-ai/bark'><img src='https://img.shields.io/github/stars/suno-ai/bark?style=social' /></a>
+<a style='display:inline-block' href='https://discord.gg/J2B2vsjKuE'><img src='https://dcbadge.vercel.app/api/server/J2B2vsjKuE?compact=true&style=flat' /></a>
+<a style="display:inline-block; margin-left: 1em" href="https://huggingface.co/spaces/suno/bark?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space%20to%20skip%20the%20queue-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a>
+</div>
+Bark is a universal text-to-audio model created by [Suno](www.suno.ai), with code publicly available [here](https://github.com/suno-ai/bark). \
+Bark can generate highly realistic, multilingual speech as well as other audio - including music, background noise and simple sound effects. \
+This demo should be used for research purposes only. Commercial use is strictly prohibited. \
+The model output is not censored and the authors do not endorse the opinions in the generated content. \
+Use at your own risk.
+"""
+
+article = """
+## 🌎 Foreign Language
+Bark supports various languages out-of-the-box and automatically determines language from input text. \
+When prompted with code-switched text, Bark will even attempt to employ the native accent for the respective languages in the same voice.
+Try the prompt:
+```
+Buenos días Miguel. Tu colega piensa que tu alemán es extremadamente malo. But I suppose your english isn't terrible.
+```
+## 🤭 Non-Speech Sounds
+Below is a list of some known non-speech sounds, but we are finding more every day. \
+Please let us know if you find patterns that work particularly well on Discord!
+* [laughter]
+* [laughs]
+* [sighs]
+* [music]
+* [gasps]
+* [clears throat]
+* — or ... for hesitations
+* ♪ for song lyrics
+* capitalization for emphasis of a word
+* MAN/WOMAN: for bias towards speaker
+Try the prompt:
+```
+" [clears throat] Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as... ♪ singing ♪."
+```
+## 🎶 Music
+Bark can generate all types of audio, and, in principle, doesn't see a difference between speech and music. \
+Sometimes Bark chooses to generate text as music, but you can help it out by adding music notes around your lyrics.
+Try the prompt:
+```
+♪ In the jungle, the mighty jungle, the lion barks tonight ♪
+```
+## 🧬 Voice Cloning
+Bark has the capability to fully clone voices - including tone, pitch, emotion and prosody. \
+The model also attempts to preserve music, ambient noise, etc. from input audio. \
+However, to mitigate misuse of this technology, we limit the audio history prompts to a limited set of Suno-provided, fully synthetic options to choose from.
+## 👥 Speaker Prompts
+You can provide certain speaker prompts such as NARRATOR, MAN, WOMAN, etc. \
+Please note that these are not always respected, especially if a conflicting audio history prompt is given.
+Try the prompt:
+```
+WOMAN: I would like an oatmilk latte please.
+MAN: Wow, that's expensive!
+```
+## Details
+Bark model by [Suno](https://suno.ai/), including official [code](https://github.com/suno-ai/bark) and model weights. \
+Gradio demo supported by 🤗 Hugging Face. Bark is licensed under a non-commercial license: CC-BY 4.0 NC, see details on [GitHub](https://github.com/suno-ai/bark).
+"""
+
+examples = [
+    ["Please surprise me and speak in whatever voice you enjoy. Vielen Dank und Gesundheit!",
+        "Unconditional"],  # , 0.7, 0.7],
+    ["Hello, my name is Suno. And, uh — and I like pizza. [laughs] But I also have other interests such as playing tic tac toe.",
+        "Speaker 1 (en)"],  # , 0.7, 0.7],
+    ["Buenos días Miguel. Tu colega piensa que tu alemán es extremadamente malo. But I suppose your english isn't terrible.",
+        "Speaker 0 (es)"],  # , 0.7, 0.7],
+]
+
+
+def gen_tts(text, history_prompt):  # , temp_semantic, temp_waveform):
+    history_prompt = PROMPT_LOOKUP[history_prompt]
+    if DEBUG_MODE:
+        audio_arr = np.zeros(SAMPLE_RATE)
+    else:
+        # , text_temp=temp_semantic, waveform_temp=temp_waveform)
+        audio_arr = generate_audio(text, history_prompt=history_prompt)
+    audio_arr = (audio_arr * 32767).astype(np.int16)
+    return (SAMPLE_RATE, audio_arr)
+
+
+css = """
+        #share-btn-container {
+            display: flex;
+            padding-left: 0.5rem !important;
+            padding-right: 0.5rem !important;
+            background-color: #000000;
+            justify-content: center;
+            align-items: center;
+            border-radius: 9999px !important;
+            width: 13rem;
+            margin-top: 10px;
+            margin-left: auto;
+            flex: unset !important;
+        }
+        #share-btn {
+            all: initial;
+            color: #ffffff;
+            font-weight: 600;
+            cursor: pointer;
+            font-family: 'IBM Plex Sans', sans-serif;
+            margin-left: 0.5rem !important;
+            padding-top: 0.25rem !important;
+            padding-bottom: 0.25rem !important;
+            right:0;
+        }
+        #share-btn * {
+            all: unset !important;
+        }
+        #share-btn-container div:nth-child(-n+2){
+            width: auto !important;
+            min-height: 0px !important;
+        }
+        #share-btn-container .wrap {
+            display: none !important;
+        }
+"""
+with gr.Blocks(css=css) as block:
+    gr.Markdown(title)
+    gr.Markdown(description)
+    with gr.Row():
+        with gr.Column():
+            input_text = gr.Textbox(
+                label="Input Text", lines=2, value=default_text, elem_id="input_text")
+            options = gr.Dropdown(
+                AVAILABLE_PROMPTS, value="Speaker 1 (en)", label="Acoustic Prompt", elem_id="speaker_option")
+            run_button = gr.Button(text="Generate Audio", type="button")
+        with gr.Column():
+            audio_out = gr.Audio(label="Generated Audio",
+                                 type="numpy", elem_id="audio_out")
+            with gr.Row(visible=False) as share_row:
+                with gr.Group(elem_id="share-btn-container"):
+                    community_icon = gr.HTML(community_icon_html)
+                    loading_icon = gr.HTML(loading_icon_html)
+                    share_button = gr.Button(
+                        "Share to community", elem_id="share-btn")
+                    share_button.click(None, [], [], _js=share_js)
+    inputs = [input_text, options]
+    outputs = [audio_out]
+    gr.Examples(examples=examples, fn=gen_tts, inputs=inputs,
+                outputs=outputs, cache_examples=True)
+    gr.Markdown(article)
+    run_button.click(fn=lambda: gr.update(visible=False), inputs=None, outputs=share_row, queue=False).then(
+        fn=gen_tts, inputs=inputs, outputs=outputs, queue=True).then(
+        fn=lambda: gr.update(visible=True), inputs=None, outputs=share_row, queue=False)
+
+block.queue()
+block.launch()
+