sooftware/conformer
[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)
This project offers a foundational component for developing highly accurate speech recognition systems. It takes raw audio sequences and processes them to generate predictions for spoken words or phonemes. If you're an AI researcher, a speech scientist, or a machine learning engineer working on advanced speech-to-text applications, this tool provides a state-of-the-art model for improved transcription.
1,109 stars.
Use this if you need a high-performance speech recognition model that combines the strengths of both local feature extraction (CNNs) and global context understanding (Transformers) for superior accuracy.
Not ideal if you are looking for a complete, out-of-the-box speech recognition application rather than a model component for integration.
Stars
1,109
Forks
188
Language
Python
License
Apache-2.0
Category
Last pushed
Jan 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/sooftware/conformer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
khanld/chunkformer
ChunkFormer: Masked Chunking Conformer For Long-Form Speech Transcription
upskyy/Squeezeformer
PyTorch implementation of "Squeezeformer: An Efficient Transformer for Automatic Speech...
WindQAQ/listen-attend-and-spell
Tensorflow implementation of "Listen, Attend and Spell" authored by William Chan. This project...
jackaduma/LAS_Mandarin_PyTorch
Listen, attend and spell Model and a Chinese Mandarin Pretrained model (中文-普通话 ASR模型)
kaituoxu/Listen-Attend-Spell
A PyTorch implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.