HF音频
facebook/unit_hifigan_HK_layer12.km2500_frame_TAT-TTS
unit_hifigan_HK_layer12.km2500_frame_TAT-TTS
Hokkien unit HiFiGAN based vocoder from fairseq:
- Trained with TAT-TTS data with 4 speakers in Taiwanese Hokkien accent. See here
for more training details.
Usage
import json
import os
from pathlib import Path
import IPython.display as ipd
from fairseq import hub_utils
from fairseq.checkpoint_utils import load_model_ensemble_and_task_from_hf_hub
from fairseq.models.speech_to_text.hub_interface import S2THubInterface
from fairseq.models.text_to_speech import CodeHiFiGANVocoder
from fairseq.models.text_to_speech.hub_interface import VocoderHubInterface
from huggingface_hub import snapshot_download
import torchaudio
cache_dir = os.getenv("HUGGINGFACE_HUB_CACHE")
# speech synthesis
library_name = "fairseq"
cache_dir = (
cache_dir or (Path.home() / ".cache" / library_name).as_posix()
)
cache_dir = snapshot_download(
f"facebook/unit_hifigan_HK_layer12.km2500_frame_TAT-TTS", cache_dir=cache_dir, library_name=library_name
)
x = hub_utils.from_pretrained(
cache_dir,
"model.pt",
".",
archive_map=CodeHiFiGANVocoder.hub_models(),
config_yaml="config.json",
fp16=False,
is_vocoder=True,
)
with open(f"{x['args']['data']}/config.json") as f:
vocoder_cfg = json.load(f)
assert (
len(x["args"]["model_path"]) == 1
), "Too many vocoder models in the input"
vocoder = CodeHiFiGANVocoder(x["args"]["model_path"][0], vocoder_cfg)
tts_model = VocoderHubInterface(vocoder_cfg, vocoder)
tts_sample = tts_model.get_model_input(unit)
wav, sr = tts_model.get_prediction(tts_sample)
ipd.Audio(wav, rate=sr)
数据统计
数据评估
关于facebook/unit_hifigan_HK_layer12.km2500_frame_TAT-TTS特别声明
本站Ai导航提供的facebook/unit_hifigan_HK_layer12.km2500_frame_TAT-TTS都来源于网络,不保证外部链接的准确性和完整性,同时,对于该外部链接的指向,不由Ai导航实际控制,在2023年5月15日 下午3:17收录时,该网页上的内容,都属于合规合法,后期网页的内容如出现违规,可以直接联系网站管理员进行删除,Ai导航不承担任何责任。
相关导航
暂无评论...