The Arabic transcription model does not provide diacritics
The model does not transcribe the diacritics anymore. I have tried the following
import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.EncDecHybridRNNTCTCBPEModel.from_pretrained(model_name="nvidia/stt_ar_fastconformer_hybrid_large_pcd_v1.0")
output = asr_model.transcribe(['/content/001 Al-Fatihah alfath.wav'])
print(output[0].text)
ุฃุนูุฐ ุจุงููู ู ู ุงูุดูุทุงู ุงูุฑุฌูู ุจุณู ุงููู ุงูุฑุญู ู ุงูุฑุญูู ุงูุญู ุฏ ููู ุฑุจ ุงูุนุงูู ูู ุงูุฑุญู ู ุงูุฑุญูู ู ุงูู ููู ุงูุฏูู ุฅูุงู ูุนุจุฏ ูุฅูุงู ูุณุชุนูู ุงูุฏูุง ุงูุตุฑุงุท ุงูู ุณุชููู ุตุฑุงุท ุงูุฐูู ุฃูุนู ุช ุนูููู ุบูุฑ ุงูู ุบุถูุจ ุนูููู ููุง ุงูุถุงููู
what do you mean it doesnt anymore? It gave diacritics before? and whats the update now?
you can try my demo .... i think it's working :
https://huggingface.co/spaces/NightPrince/Arabic-Transcriber-Pro
did this model actually ever output diacritics? because it is not doing that currently.
https://huggingface.co/spaces/hana92/nvidia-diacritics