metadata
datasets:
- DavronSherbaev/uzbekvoice-filtered
- mozilla-foundation/common_voice_17_0
language:
- uz
metrics:
- wer
base_model:
- nvidia/stt_en_fastconformer_transducer_large
pipeline_tag: automatic-speech-recognition
WER Uzbekvoice 6.23
pip install nemo_toolkit['asr']
wget https://huggingface.co/Saidakmal/ASR_nvidia_fastconformer/resolve/main/fast_conf_uz_1024_tokens.nemo?download=true
import nemo.collections.asr as nemo_asr
from omegaconf import OmegaConf
asr_model = nemo_asr.models.EncDecHybridRNNTCTCBPEModel.restore_from(
"fast_conf_uz_1024_tokens.nemo"
)
output = asr_model.transcribe(["path_audio"])
print(output[0] if isinstance(output[0], str) else output[0].text)