Downloads · 30 days
3
100% of all-time downloads
zh_openslr38
espnet/zh_openslr38
zh_openslr38 is a automatic speech recognition model from espnet. Use it when you need speech turned into text. The card lists the license as mit.
All-time downloads
3
Public
Repo size
6.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth5.8 GB · 88%
At a glance
- Task
- Automatic Speech Recognition
- License
- mit
- Access
- Public
- Created
- Mar 22, 2022
- Updated
- Sep 19, 2026
- SHA
- 8c9c40ff
Model card
From the Hugging Face model README
Usage
import librosa
from espnet2.bin.asr_inference import Speech2Text
speech2text = Speech2Text.from_pretrained(model_tag="espnet/zh_openslr38")
# librosa resamples and mixes to one channel, so any file works; 16000 is
# what nearly every espnet recogniser is trained on - check this model's
# config if its audio is not 16 kHz
speech, rate = librosa.load("audio.wav", sr=16000, mono=True)
text, *_ = speech2text(speech)[0]
print(text)
- Task
- Automatic Speech Recognition
- License
- mit
- Created
- Mar 22, 2022
- Updated
- Sep 19, 2026