Merge remote-tracking branch 'origin/main'

app.py

@@ -1,177 +1,68 @@
-
+"""
+Prepare the Shakespeare dataset for character-level language modeling.
+So instead of encoding with GPT-2 BPE tokens, we just map characters to ints.
+Will save train.bin, val.bin containing the ids, and meta.pkl containing the
+encoder and decoder and some other related info.
+"""
+import os
+import pickle
+import requests
 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
+# download the tiny shakespeare dataset
+input_file_path = os.path.join(os.path.dirname(__file__), 'input.txt')
+if not os.path.exists(input_file_path):
+    data_url = 'https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt'
+    with open(input_file_path, 'w') as f:
+        f.write(requests.get(data_url).text)
 
-if not DEBUG_MODE:
-    _ = preload_models()
+with open(input_file_path, 'r') as f:
+    data = f.read()
+print(f"length of dataset in characters: {len(data):,}")
 
-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"
+# get all the unique characters that occur in this text
+chars = sorted(list(set(data)))
+vocab_size = len(chars)
+print("all the unique characters:", ''.join(chars))
+print(f"vocab size: {vocab_size:,}")
 
-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."
+# create a mapping from characters to integers
+stoi = { ch:i for i,ch in enumerate(chars) }
+itos = { i:ch for i,ch in enumerate(chars) }
+def encode(s):
+    return [stoi[c] for c in s] # encoder: take a string, output a list of integers
+def decode(l):
+    return ''.join([itos[i] for i in l]) # decoder: take a list of integers, output a string
 
-title = "# 🐶 Bark</div>"
+# create the train and test splits
+n = len(data)
+train_data = data[:int(n*0.9)]
+val_data = data[int(n*0.9):]
 
-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).
-"""
+# encode both to integers
+train_ids = encode(train_data)
+val_ids = encode(val_data)
+print(f"train has {len(train_ids):,} tokens")
+print(f"val has {len(val_ids):,} tokens")
 
-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)
+# export to bin files
+train_ids = np.array(train_ids, dtype=np.uint16)
+val_ids = np.array(val_ids, dtype=np.uint16)
+train_ids.tofile(os.path.join(os.path.dirname(__file__), 'train.bin'))
+val_ids.tofile(os.path.join(os.path.dirname(__file__), 'val.bin'))
 
-block.queue()
-block.launch()
+# save the meta information as well, to help us encode/decode later
+meta = {
+    'vocab_size': vocab_size,
+    'itos': itos,
+    'stoi': stoi,
+}
+with open(os.path.join(os.path.dirname(__file__), 'meta.pkl'), 'wb') as f:
+    pickle.dump(meta, f)
 
+# length of dataset in characters:  1115394
+# all the unique characters:
+#  !$&',-.3:;?ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz
+# vocab size: 65
+# train has 1003854 tokens
+# val has 111540 tokens