An Automatic Speech Recognition(ASR) for English language trained on LibriSpeech dataset using Conformer.
Project description
english_asr
An Automatic Speech Recognition (ASR) models in TensorFlow Lite (TFLite) for Speech-To-Text conversion.
Installation
- pip3 install english-asr
Supported Model
- Conformer Transducer using LibriSpeech dataset.
How To Run
from english_asr.conformer import get_text_from_speech
out = get_text_from_speech('audio.wav')```
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
english_asr-1.2.tar.gz
(1.8 kB
view hashes)
Built Distribution
Close
Hashes for english_asr-1.2-py2.py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 350789529b579539ba380c302b4190f5b009dbfe1f584d101bb1c18816dcb4a4 |
|
| MD5 | 96f44e17437715fe0d8241ec5729e06b |
|
| BLAKE2b-256 | d6f701b11ed2557a42a107fb1f845f03dea780d29858058f74970804302da383 |
