Thanks Nickolay. I noticed it and fixed the error. It was my fault.
I get an error: "Failed to open c:/Sphinx/geo/etc/feat.params: No such file or directory at C:\Sphinx\sphinxtrain\scripts\lib/SphinxTrain" Then process is stucked giving this message: Waiting for c:/Sphinx/geo/model_parameters/geo.ci_cont/mixture_weights I could not find any ERROR or WARNING in log files. For another set of data everyting works well, so I guess it is not becasuse of sphinx but for my data.
Thanks. I resolved the issue.
How can I generate match file using pocketsphinx_batch from cmd?
I am not experienced in Linux. This is why I prefer Windows. As I see at one point I should move to Linux. I noticed one strange thing. May be it tells something. During every training, files like other_test.transcription6940 are generated (attached). I don't get error messages and warnings, but I think something goes wrang with these files.
pocketsphinx_continuous works well. Actually everyting runs well if I copy "other-1-1.match" file into results folder. I downloaded this file from internet. The problem is that I can not regenerate this file.
Yes, I compiled them. Now I dowloaded compiled versions. Unfortunately the same error.
Changed $CFG_G2P_MODEL= 'no'; but getting the same error
other.g2p.evaluate.log file says: Traceback (most recent call last): File "C:\Sphinx\sphinxtrain\scripts\0000.g2p_train\evaluate.py", line 111, in <module> process_testset( test_file, wordlist, ref_file ) File "C:\Sphinx\sphinxtrain\scripts\0000.g2p_train\evaluate.py", line 42, in process_testset for entry in open(testfile): FileNotFoundError: [Errno 2] No such file or directory: 'c:/Sphinx/other/g2p/other.test'</module> I don't know why "other.test" is not created.
I'm getting the following error and could not resolve the problem: Can't open c:/Sphinx/geo1/result/geo1-1-1.match word_align.pl failed with error code 65280 at C:\Sphinx\sphinxtrain\scripts\decode\slave.pl line 173. The project is attached. Your advise would be much appriciated.
It is working. Many thanks Nickolay!
Thanks. I prefer to modify sphinx_train.cfg at this stage. I thought I was using ci_cont model. Here is my sphinx_train.cfg.
Attached
Can someone help with this error? ERROR: "acmod.c", line 83: Folder 'c:/Sphinx/other/model_parameters/other.cd_cont_200' does not contain acoustic model definition 'mdef' The folder 'other.cd_cont_200 ' is not created at all. I checked for log files but could not notice any obvious problem.
Thanks for advice.
I have the same problem: "ERROR: lda.py failed to create LDA transform with status 0" I checked for numpy, scipy. They are OK . I tried to run lda.py from cmd, but it is not running: Unable to create process using 'C:\Users\Rati Skhirtladze\AppData\Local\Programs\Python\Python38-32\python.exe "C:\Sphinx\sphinxtrain\python\cmusphinx\lda.py" ' I think the issue is that I am running lda.py on Windows. I tried to install Debian as Orest mentioned, but without success: "WslRegisterDistribution failed...
I resoved the problem...
Can someone help with this error? At "MODULE: 0000 train grapheme-to-phoneme model":"Phase 2: Training g2p model...": the log file says: '"g2p_train"' is not recognized as an internal or external command, operable program or batch file.
Thanks to A13X10 I could fix this problem: I have made change to ...sphinxtrain\scripts\lib\SphinxTrain\Config.pm. I changed line 51 with "$ST::CFG_FILE = "./etc/sphinx_train.cfg";"
For many bottles :)
Dear CMUSphinx, Is possible to build Speech recognition program for Georgian Language with CMUSphinx and what kind of support we may expect from you? Rati
Thank you so much for this information.
Dear all, As I learned from this link http://espeak.sourceforge.net/languages.html espeak supports Georgian but it is on early stage. Could you please guide me how can I learn more about this issue and how can I participate in the project?