espnet/MInDS-14_es-ES
013
Usage
import librosa
from espnet2.bin.asr_inference import Speech2Text
speech2text = Speech2Text.from_pretrained(model_tag="espnet/MInDS-14_es-ES")
# 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)RESULTS
Environments
- date:
Mon Mar 14 22:28:37 UTC 2022 - python version:
3.8.12 | packaged by conda-forge | (default, Jan 30 2022, 23:42:07) [GCC 9.4.0] - espnet version:
espnet 0.10.7a1 - pytorch version:
pytorch 1.10.1 - Git hash:
d5322b2dc4844dce1d14268b6848607e2a3dee21 - Commit date:
Mon Mar 14 20:21:16 2022 +0000