Kokoro 82M

🚀 Kokoro - 輕量級高效文本轉語音模型

Kokoro是一個擁有8200萬參數的開源權重文本轉語音（TTS）模型。儘管架構輕量，但它能提供與大型模型相媲美的質量，同時速度更快、成本更低。其權重採用Apache許可證，可在從生產環境到個人項目的任何場景中部署。

⬆️ Kokoro已升級到v1.0版本！ 查看版本發佈。

✨ 現在你可以通過pip install kokoro進行安裝！查看使用方法。

• 版本發佈
• 使用方法
• SAMPLES.md ↗️
• VOICES.md ↗️
• 模型信息
• 訓練詳情
• 知識共享署名說明
• 致謝

🚀 快速開始

你可以通過以下命令安裝Kokoro推理庫：

pip install kokoro

安裝完成後，你可以參考下面的使用示例進行操作。

✨ 主要特性

• 輕量級架構：僅8200萬參數，卻能提供與大型模型相媲美的語音質量。
• 高效性能：速度更快，成本更低，適合各種場景部署。
• 多語言支持：支持美式英語、英式英語、法語、印地語等多種語言。
• 開源權重：採用Apache許可證，可自由用於生產環境和個人項目。

📦 安裝指南

你可以使用pip命令安裝Kokoro：

pip install kokoro

安裝鏈接：pip install kokoro

💻 使用示例

基礎用法

# 1️⃣ 安裝kokoro
!pip install -q kokoro>=0.3.4 soundfile
# 2️⃣ 安裝espeak，用於英語OOD回退和一些非英語語言
!apt-get -qq -y install espeak-ng > /dev/null 2>&1
# 🇪🇸 'e' => 西班牙語 es
# 🇫🇷 'f' => 法語 fr-fr
# 🇮🇳 'h' => 印地語 hi
# 🇮🇹 'i' => 意大利語 it
# 🇧🇷 'p' => 巴西葡萄牙語 pt-br

# 3️⃣ 初始化一個管道
from kokoro import KPipeline
from IPython.display import display, Audio
import soundfile as sf
# 🇺🇸 'a' => 美式英語, 🇬🇧 'b' => 英式英語
# 🇯🇵 'j' => 日語: pip install misaki[ja]
# 🇨🇳 'z' => 普通話: pip install misaki[zh]
pipeline = KPipeline(lang_code='a') # <= 確保lang_code與語音匹配

# 此文本僅用於演示目的，訓練期間未見過
text = '''
The sky above the port was the color of television, tuned to a dead channel.
"It's not like I'm using," Case heard someone say, as he shouldered his way through the crowd around the door of the Chat. "It's like my body's developed this massive drug deficiency."
It was a Sprawl voice and a Sprawl joke. The Chatsubo was a bar for professional expatriates; you could drink there for a week and never hear two words in Japanese.

These were to have an enormous impact, not only because they were associated with Constantine, but also because, as in so many other areas, the decisions taken by Constantine (or in his name) were to have great significance for centuries to come. One of the main issues was the shape that Christian churches were to take, since there was not, apparently, a tradition of monumental church buildings when Constantine decided to help the Christian church build a series of truly spectacular structures. The main form that these churches took was that of the basilica, a multipurpose rectangular structure, based ultimately on the earlier Greek stoa, which could be found in most of the great cities of the empire. Christianity, unlike classical polytheism, needed a large interior space for the celebration of its religious services, and the basilica aptly filled that need. We naturally do not know the degree to which the emperor was involved in the design of new churches, but it is tempting to connect this with the secular basilica that Constantine completed in the Roman forum (the so-called Basilica of Maxentius) and the one he probably built in Trier, in connection with his residence in the city at a time when he was still caesar.

[Kokoro](/kˈOkəɹO/) is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, [Kokoro](/kˈOkəɹO/) can be deployed anywhere from production environments to personal projects.
'''
# text = '「もしおれがただ偶然、そしてこうしようというつもりでなくここに立っているのなら、ちょっとばかり絶望するところだな」と、そんなことが彼の頭に思い浮かんだ。'
# text = '中國人民不信邪也不怕邪，不惹事也不怕事，任何外國不要指望我們會拿自己的核心利益做交易，不要指望我們會吞下損害我國主權、安全、發展利益的苦果！'
# text = 'Los partidos políticos tradicionales compiten con los populismos y los movimientos asamblearios.'
# text = 'Le dromadaire resplendissant déambulait tranquillement dans les méandres en mastiquant de petites feuilles vernissées.'
# text = 'ट्रांसपोर्टरों की हड़ताल लगातार पांचवें दिन जारी, दिसंबर से इलेक्ट्रॉनिक टोल कलेक्शनल सिस्टम'
# text = "Allora cominciava l'insonnia, o un dormiveglia peggiore dell'insonnia, che talvolta assumeva i caratteri dell'incubo."
# text = 'Elabora relatórios de acompanhamento cronológico para as diferentes unidades do Departamento que propõem contratos.'

# 4️⃣ 循環生成、顯示和保存音頻文件。
generator = pipeline(
    text, voice='af_heart', # <= 在此更改語音
    speed=1, split_pattern=r'\n+'
)
for i, (gs, ps, audio) in enumerate(generator):
    print(i)  # i => 索引
    print(gs) # gs => 字符/文本
    print(ps) # ps => 音素
    display(Audio(data=audio, rate=24000, autoplay=i==0))
    sf.write(f'{i}.wav', audio, 24000) # 保存每個音頻文件

📚 詳細文檔

版本發佈

模型信息

訓練詳情

• 訓練數據：Kokoro僅在許可/無版權音頻數據和國際音標（IPA）音素標籤上進行訓練。許可/無版權音頻的示例包括：
  • 公共領域音頻
  • 採用Apache、MIT等許可證的音頻
  • 大型供應商的封閉^[2] TTS模型生成的合成音頻^[1]
    [1] https://copyright.gov/ai/ai_policy_guidance.pdf
    [2] 不使用開源TTS模型或“自定義語音克隆”生成的合成音頻
• 總數據集大小：幾百小時的音頻
• 總訓練成本：使用A100 80GB顯存進行1000小時訓練，約1000美元

知識共享署名說明

以下采用CC BY許可證的音頻是訓練Kokoro v1.0所用數據集的一部分。

致謝

• 🛠️ 感謝@yl4579設計了StyleTTS 2架構。
• 🏆 感謝@Pendrokar將Kokoro納入TTS Spaces Arena。
• 📊 感謝所有貢獻合成訓練數據的人員。
• ❤️ 特別感謝所有計算資源贊助商。
• 👾 Discord服務器：https://discord.gg/QuGxSWBfQy
• 🪽 Kokoro是一個日語單詞，意為“心”或“精神”。Kokoro也是《終結者》系列中的一個AI的名字。

📄 許可證

本項目採用Apache-2.0許可證。