CiscoDevNet/g2p_seq2seq_pytorch
Grapheme to phoneme model for PyTorch
This tool generates spoken pronunciations (phonemes) for written words, helping you convert text into sound. You input a word, and it outputs the sequence of sounds that make up its pronunciation, optionally including stress. It's designed for developers building systems that need to process or generate speech.
No commits in the last 6 months.
Use this if you are developing automatic speech recognition systems, text-to-speech engines, or other natural language processing applications that require converting text to phonemes.
Not ideal if you need a non-developer-focused, out-of-the-box solution for speech synthesis or analysis without needing to integrate a G2P model programmatically.
Stars
43
Forks
12
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 21, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/CiscoDevNet/g2p_seq2seq_pytorch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
thewh1teagle/phonikud
Hebrew grapheme to phoneme (G2P)
Wikidepia/g2p-id
Indonesian Grapheme-to-Phoneme (IPA notation)
GitYCC/g2pW
Chinese Mandarin Grapheme-to-Phoneme Converter. 中文轉注音或拼音 (INTERSPEECH 2022)
stefantaubert/pinyin-to-ipa
Command-line interface and Python library to transcribe pinyin to IPA. The tones are attached to...
AdolfVonKleist/Phonetisaurus
Phonetisaurus G2P