nvidia
/

stt_en_conformer_transducer_xlarge

Automatic Speech Recognition

hf-asr-leaderboard

Model card Files Files and versions Community

smajumdar94 commited on Jun 28, 2022

Commit

1d8eb0f

•

1 Parent(s): 5ee93ed

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -21,7 +21,7 @@ tags:
 - automatic-speech-recognition
 - speech
 - audio
-- CTC
 - Conformer
 - Transformer
 - pytorch
@@ -211,7 +211,7 @@ 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).

 - automatic-speech-recognition
 - speech
 - audio
+- Transducer
 - Conformer
 - Transformer
 - pytorch
 ## 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).