thennal/GMaSC
Viewer • Updated • 2k • 88 • 2
How to use kurianbenoy/whisper-small-ml-gmasc with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("automatic-speech-recognition", model="kurianbenoy/whisper-small-ml-gmasc") # Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("kurianbenoy/whisper-small-ml-gmasc")
model = AutoModelForSpeechSeq2Seq.from_pretrained("kurianbenoy/whisper-small-ml-gmasc", device_map="auto")On Evaluating the model:
In Mozilla CommonVoice dataset:
WER - 41.12 CER - 21.24
In SMC dataset:
WER - 32.09 CER - 16.89