POWSM-CTC is a variant of
POWSM
, the first phonetic foundation model that can perform four phone-related tasks.
Its multi-task encoder-CTC structure is based on
OWSM-CTC
, and trained on
IPAPack++
, the same dataset as POWSM.
This model is proposed together with our paper
PRiSM
, the first open-source benchmark for phone recognition systems.
Its decoding is much faster than encoder-decoder models, with similar or enhanced PR performance on unseen domain.
Our models are trained on 16kHz audio with a fixed duration of 20s. When using the pre-trained model, please ensure the input speech is 16kHz and pad or truncate it to 20s.
To distinguish phone entries from BPE tokens that share the same Unicode, we enclose every phone in slashes and treat them as special tokens. For example, /pʰɔsəm/ would be tokenized as /pʰ//ɔ//s//ə//m/.
from espnet2.bin.s2t_inference_ctc import Speech2TextGreedySearch
s2t = Speech2TextGreedySearch.from_pretrained(
"espnet/powsm_ctc",
device="cuda",
use_flash_attn=True,
lang_sym='<unk>',
task_sym='<pr>',
)
res = s2t.batch_decode(
["audio1.wav", "audio2.wav"], # a list of audios (path or 1-D array/tensor)
batch_size=16,
) # res is a list of str
Citations
@article{prism,
title={PRiSM: Benchmarking Phone Realization in Speech Models},
author={Shikhar Bharadwaj and Chin-Jou Li and Yoonjae Kim and Kwanghee Choi and Eunjung Yeo and Ryan Soh-Eun Shim and Hanyu Zhou and Brendon Boldt and Karen Rosero Jacome and Kalvin Chang and Darsh Agrawal and Keer Xu and Chao-Han Huck Yang and Jian Zhu and Shinji Watanabe and David R. Mortensen},
year={2026},
eprint={2601.14046},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2601.14046},
}
Runs of espnet powsm_ctc on huggingface.co
112
Total runs
15
24-hour runs
22
3-day runs
35
7-day runs
53
30-day runs
More Information About powsm_ctc huggingface.co Model
powsm_ctc huggingface.co is an AI model on huggingface.co that provides powsm_ctc's model effect (), which can be used instantly with this espnet powsm_ctc model. huggingface.co supports a free trial of the powsm_ctc model, and also provides paid use of the powsm_ctc. Support call powsm_ctc model through api, including Node.js, Python, http.
powsm_ctc huggingface.co is an online trial and call api platform, which integrates powsm_ctc's modeling effects, including api services, and provides a free online trial of powsm_ctc, you can try powsm_ctc online for free by clicking the link below.
espnet powsm_ctc online free url in huggingface.co:
powsm_ctc is an open source model from GitHub that offers a free installation service, and any user can find powsm_ctc on GitHub to install. At the same time, huggingface.co provides the effect of powsm_ctc install, users can directly use powsm_ctc installed effect in huggingface.co for debugging and trial. It also supports api for free installation.