Instructions to use Peacockery/citrinet-256-phoneme-en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use Peacockery/citrinet-256-phoneme-en with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("Peacockery/citrinet-256-phoneme-en") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Citrinet-256 Phoneme EN
This repository stores the full P003 Citrinet-256 phoneme model artifact trained on the train_clean_100 ARPABET-41 setup.
Training Run
- Base model:
nvidia/stt_en_citrinet_256_ls - Fine-tuning target: ARPABET-41 plus tokenizer control tokens
- Tokenizer size:
44 - Full training budget:
3epochs - Final report:
report.json - Primary artifact:
artifacts/citrinet_256_p2b_trainclean100_local_full_s3.nemo
Result Snapshot
- Global step:
5353 - Seed:
17 - Validation WER:
0.2281 - Validation loss:
65.32 - W&B run:
x6zaxexu
Intended Use
This artifact is intended to be consumed by the P003 scoring pipeline through the nemo: backend contract. It is not an HF AutoModelForCTC checkpoint.
Example backend string:
nemo:Peacockery/citrinet-256-phoneme-en
- Downloads last month
- 52