nvidia
/

stt_en_fastconformer_transducer_xlarge

Automatic Speech Recognition

hf-asr-leaderboard

Model card Files Files and versions Community

nithinraok commited on Jun 12, 2023

Commit

af957d4

•

1 Parent(s): 29467cc

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -147,7 +147,7 @@ img {
 This model transcribes speech in lower case English alphabet.
-It is a "large" version of FastConformer Transducer (around 618M parameters) model.
 See the [model architecture](#model-architecture) section and [NeMo documentation](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#fast-conformer) for complete architecture details.
 ## NVIDIA NeMo: Training

 This model transcribes speech in lower case English alphabet.
+It is a "extra large" version of FastConformer Transducer (around 618M parameters) model.
 See the [model architecture](#model-architecture) section and [NeMo documentation](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#fast-conformer) for complete architecture details.
 ## NVIDIA NeMo: Training