English ASR models
Models are trained on the si-84 subset of the LDC WSJ0 corpus. Both MFCC and PLP models are provided, with two phonetic representations (gam and arpabet) based on the Unilex dictionary. In addition, the MFCC arpabet models are provided with the AMR codec. The release is subject to the LDC conditions; that is, the acoustic models are released as a derived work, but for research only.
The link address is: http://data.cstr.ed.ac.uk/emime/ASR-models-Eng.tar.gz