库名称: fairseq 任务: 文本转语音 标签:

• fairseq
• 音频
• 文本转语音 语言: 中文 数据集:
• common_voice
• css10 小部件示例:
• 文本: "您好，这是试运行。" 示例标题: "Hello, this is a test run."

tts_transformer-zh-cv7_css10

基于fairseq S^2的Transformer文本转语音模型（论文/代码）：

• 简体中文
• 单人女声
• 基于Common Voice v7预训练，在CSS10上微调

使用方法

from fairseq.checkpoint_utils import load_model_ensemble_and_task_from_hf_hub
from fairseq.models.text_to_speech.hub_interface import TTSHubInterface
import IPython.display as ipd


models, cfg, task = load_model_ensemble_and_task_from_hf_hub(
    "facebook/tts_transformer-zh-cv7_css10",
    arg_overrides={"vocoder": "hifigan", "fp16": False}
)
model = models[0]
TTSHubInterface.update_cfg_with_data_cfg(cfg, task.data_cfg)
generator = task.build_generator(model, cfg)

text = "您好，这是试运行。"

sample = TTSHubInterface.get_model_input(task, text)
wav, rate = TTSHubInterface.get_prediction(task, model, generator, sample)

ipd.Audio(wav, rate=rate)

另见fairseq S^2示例。

引用文献

@inproceedings{wang-etal-2021-fairseq,
    title = "fairseq S{\^{}}2: 可扩展且可集成的语音合成工具包",
    author = "Wang, Changhan  and
      Hsu, Wei-Ning  and
      Adi, Yossi  and
      Polyak, Adam  and
      Lee, Ann  and
      Chen, Peng-Jen  and
      Gu, Jiatao  and
      Pino, Juan",
    booktitle = "2021年自然语言处理实证方法会议系统演示论文集",
    month = "11月",
    year = "2021",
    address = "线上及多米尼加共和国蓬塔卡纳",
    publisher = "计算语言学协会",
    url = "https://aclanthology.org/2021.emnlp-demo.17",
    doi = "10.18653/v1/2021.emnlp-demo.17",
    pages = "143--152",
}