Eric Riebling

Although it should build either way, I'm wondering if this has to do with how the code was configured; 1. Are you building with or without CUDA GPU support? 2....

Not sure either; have we tried building against Cuda 9.0 yet? Thus far we've been sticking to 8.0, but 9 is the new default, and may have differences like the...

Possibly not, because what if the dictionary lists most frequent first? If the compromise is to choose only one possible pronunciation, it should be the most common one! So I...

You're right, there is no general format that data sets must conform to; for each data format, there are local, non-general preparation steps. Switchboard, WSJ, Tedlium are all different. For...

On 11/07/2016 01:42 AM, Sundy1219 wrote: > Hello , I am studying the eesen scripts in the directory ars_egs/hkust/v1 now. but I cannot access to LDC2005S15 and LDC2005T32 corpus ....

I'm not really sure what to do with those files, but perhaps they are just a duplicate of data, but in a different format? See: http://cmusphinx.sourceforge.net/wiki/tutoriallm They mention that the...

Eesen has all the scripts you will need, if you look at a full experiment for example asr_egs/tedlium/v2-30ms/run_ctc_phn.sh. The decoding and testing happen at the end, the decode_ctc_lat.sh script decodes...

Sorry, my interpretation of "testing" was not what you meant. And also sorry that I don't know of any ways of testing only the TLG.fst decoding graph by itself. I...

Any results from your end @xfwu ? (Yajie's results and response will not be available)

Would that be the data_dir referred to in the data preparation instructions? (for example `local/tedlium_prepar_data.sh`) ``` # 2014 Brno University of Technology (Author: Karel Vesely) # Apache 2.0 # To...