# Load model directly
from transformers import AutoProcessor, AutoModelForCTC
processor = AutoProcessor.from_pretrained("Arunodhayan/German_ASR")
model = AutoModelForCTC.from_pretrained("Arunodhayan/German_ASR")Quick Links
language:
- de license: apache-2.0 tags:
- automatic-speech-recognition
- common_voice
- generated_from_trainer datasets:
- common_voice_de model-index:
- name: wav2vec2-large-xlsr-36
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 9
type: mozilla-foundation/common_voice_9_0
args: de
metrics:
- name: Test WER type: wer value: 0.3432458541265
- name: Test CER type: cer value: 0.19564654665564
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 9
type: mozilla-foundation/common_voice_9_0
args: de
metrics:
- Downloads last month
- 9
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Arunodhayan/German_ASR")