Automatic Speech Recognition
ESPnet
multilingual
audio
speech-translation
language-identification
Eval Results
Instructions to use espnet/owsm_ctc_v3.1_1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use espnet/owsm_ctc_v3.1_1B with ESPnet:
from espnet2.bin.asr_inference import Speech2Text model = Speech2Text.from_pretrained( "espnet/owsm_ctc_v3.1_1B" ) speech, rate = soundfile.read("speech.wav") text, *_ = model(speech)[0] - Notebooks
- Google Colab
- Kaggle
Unauthorized
#1
by pplantinga - opened
When trying to load the model using the code from the model card, I get the following:
huggingface_hub.errors.HfHubHTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/api/models/espnet/owsm_ctc_v3.1_1B/revision/main (Request ID: Root=1-67b60740-1caca34a65a1c7f5110c5e78;4b49b011-98c8-4a7c-9032-1580d67e1e0b)
Invalid credentials in Authorization header
Do I need to do something to get authorized to use this model?
I was not properly authenticated w/ hugginface
pplantinga changed discussion status to closed