Instructions to use theodotus/stt_ua_fastconformer_hybrid_large_pc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use theodotus/stt_ua_fastconformer_hybrid_large_pc with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("theodotus/stt_ua_fastconformer_hybrid_large_pc") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
metadata
language:
- uk
library_name: nemo
datasets:
- mozilla-foundation/common_voice_10_0
- Yehor/ukrainian-tts-mykyta
- Yehor/ukrainian-tts-lada
- Yehor/ukrainian-tts-tetiana
tags:
- automatic-speech-recognition
model-index:
- name: stt_ua_fastconformer_hybrid_large_pc
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Mozilla Common Voice 10.0
type: mozilla-foundation/common_voice_10_0
config: clean
split: test
args:
language: uk
metrics:
- name: Test WER
type: wer
value: 7.1
license: mit
FastConformer Hybrid Transducer-CTC Large P&C (uk-UA)
Attribution
As initial checkpoint used stt_ua_fastconformer_hybrid_large_pc by NVIDIA licensed under CC-BY-4.0