search

cywang97 / StreamingTransformer

Apache License 2.0
271 stars 42 forks source link

How can I get the the ''/path/to/model'' in Step 2. Viterbi decoding? #2

Closed Gqwert123 closed 4 years ago

Gqwert123 commented 4 years ago

Hi, I am confused how can I get the the ''/path/to/model'' in Step 2. Viterbi decoding? Step 2. Viterbi decoding To train a TA based streaming Transformer, the alignments between CTC paths and transcriptions are required. In our work, we apply Viterbi decoding using the offline Transformer model.

cd egs/librispeech/asr1 ./viterbi_decode.sh /path/to/model

Thanks a lot.

cywang97 commented 4 years ago

Hi, In my experiment, I simply use the offline model provided by ESPnet to perform viterbi decoding. (https://github.com/espnet/espnet/blob/master/egs/librispeech/asr1/RESULTS.md) You can also train an offline model by yourself using e2e_asr_transformer.py and set streaming argument to False.

Gqwert123 commented 4 years ago

Hi, In my experiment, I simply use the offline model provided by ESPnet to perform viterbi decoding. (https://github.com/espnet/espnet/blob/master/egs/librispeech/asr1/RESULTS.md) You can also train an offline model by yourself using e2e_asr_transformer.py and set streaming argument to False.

Thanks a lot!