Changhan's picture
library_name: fairseq
task: text-to-speech
- fairseq
- audio
- text-to-speech
- multi-speaker
language: en
- common_voice
- text: "Hello, this is a test run."
example_title: "Hello, this is a test run."
# tts_transformer-en-200_speaker-cv4
[Transformer]( text-to-speech model from fairseq S^2 ([paper]([code](
- English
- 200 male/female voices (random speaker when using the widget)
- Trained on [Common Voice v4](
## Usage
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(
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 = "Hello, this is a test run."
sample = TTSHubInterface.get_model_input(task, text)
wav, rate = TTSHubInterface.get_prediction(task, model, generator, sample)
ipd.Audio(wav, rate=rate)
See also [fairseq S^2 example](
## Citation
title = "fairseq S{\^{}}2: A Scalable and Integrable Speech Synthesis Toolkit",
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 = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "",
doi = "10.18653/v1/2021.emnlp-demo.17",
pages = "143--152",