nvidia
/

stt_ca_conformer_transducer_large

Automatic Speech Recognition

hf-asr-leaderboard

Model card Files Files and versions Community

steveheh commited on Jul 18, 2022

Commit

7871f4d

•

1 Parent(s): c0a65ce

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -103,7 +103,7 @@ Conformer-Transducer model is an autoregressive variant of Conformer model [1] f
 ## Training
-The NeMo toolkit [3] was used for training the models for over several hundred epochs. These model are trained with this [example script](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/asr_ctc/speech_to_text_ctc_bpe.py) and this [base config](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/conf/conformer/conformer_ctc_bpe.yaml).
 The tokenizers for these models were built using the text transcripts of the train set with this [script](https://github.com/NVIDIA/NeMo/blob/main/scripts/tokenizers/process_asr_text_tokenizer.py).

 ## Training
+The NeMo toolkit [3] was used for training the models for over several hundred epochs. These model are trained with this [example script](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/asr_transducer/speech_to_text_rnnt_bpe.py) and this [base config](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/conf/conformer/conformer_transducer_bpe.yaml).
 The tokenizers for these models were built using the text transcripts of the train set with this [script](https://github.com/NVIDIA/NeMo/blob/main/scripts/tokenizers/process_asr_text_tokenizer.py).