search

SeanNaren / deepspeech.torch

Speech Recognition using DeepSpeech2 network and the CTC activation function.
MIT License
260 stars 73 forks source link

Error Sample Rate 8khz #96

Closed stephenvxx closed 6 years ago

stephenvxx commented 7 years ago

I had a error :

/home/datvt12/torch/install/share/lua/5.1/cudnn/init.lua:162: Error in CuDNN: CUDNN_STATUS_BAD_PARAM (cudnnGetConvolutionNdForwardOutputDim) stack traceback: [C]: in function 'error' /home/datvt12/torch/install/share/lua/5.1/cudnn/init.lua:162: in function 'errcheck' ...torch/install/share/lua/5.1/cudnn/SpatialConvolution.lua:140: in function 'createIODescriptors' ...torch/install/share/lua/5.1/cudnn/SpatialConvolution.lua:188: in function <...torch/install/share/lua/5.1/cudnn/SpatialConvolution.lua:186> [C]: in function 'xpcall' /home/datvt12/torch/install/share/lua/5.1/nn/Container.lua:63: in function 'rethrowErrors' /home/datvt12/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function </home/datvt12/torch/install/share/lua/5.1/nn/Sequential.lua:41> [C]: in function 'xpcall' /home/datvt12/torch/install/share/lua/5.1/nn/Container.lua:63: in function 'rethrowErrors' /home/datvt12/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function </home/datvt12/torch/install/share/lua/5.1/nn/Sequential.lua:41> [C]: in function 'xpcall' .../datvt12/torch/install/share/lua/5.1/threads/threads.lua:234: in function 'callback' /home/datvt12/torch/install/share/lua/5.1/threads/queue.lua:65: in function </home/datvt12/torch/install/share/lua/5.1/threads/queue.lua:41> [C]: in function 'pcall' /home/datvt12/torch/install/share/lua/5.1/threads/queue.lua:40: in function 'dojob' [string " local Queue = require 'threads.queue'..."]:13: in main chunk

WARNING: If you see a stack trace below, it doesn't point to the place where this error occurred. Please use only the one above. stack traceback: [C]: in function 'error' /home/datvt12/torch/install/share/lua/5.1/nn/Container.lua:67: in function 'rethrowErrors' /home/datvt12/torch/install/share/lua/5.1/nn/Sequential.lua:44: in function </home/datvt12/torch/install/share/lua/5.1/nn/Sequential.lua:41> [C]: in function 'xpcall' .../datvt12/torch/install/share/lua/5.1/threads/threads.lua:234: in function 'callback' /home/datvt12/torch/install/share/lua/5.1/threads/queue.lua:65: in function </home/datvt12/torch/install/share/lua/5.1/threads/queue.lua:41> [C]: in function 'pcall' /home/datvt12/torch/install/share/lua/5.1/threads/queue.lua:40: in function 'dojob' [string " local Queue = require 'threads.queue'..."]:13: in main chunk stack traceback: [C]: in function 'error' .../datvt12/torch/install/share/lua/5.1/threads/threads.lua:183: in function 'dojob' .../datvt12/torch/install/share/lua/5.1/threads/threads.lua:264: in function 'synchronize' ...2/torch/install/share/lua/5.1/cunn/DataParallelTable.lua:737: in function 'exec' ...2/torch/install/share/lua/5.1/cunn/DataParallelTable.lua:197: in function 'forward' ./Network.lua:134: in function 'opfunc' /home/datvt12/torch/install/share/lua/5.1/optim/sgd.lua:44: in function 'sgd' ./Network.lua:158: in function 'trainNetwork' Train.lua:43: in main chunk [C]: in function 'dofile' ...vt12/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk [C]: at 0x00405ea0

In Deepspeechmodel.lua, i change rnnInputsize = 1 * 81 ( Because size output :20x1x81x13) Please help me ! @SeanNaren

stephenvxx commented 7 years ago

@AdolfVonKleist

SeanNaren commented 7 years ago

What dataset are you training on?

stephenvxx commented 7 years ago

I use my dataset (Be formatted as AN4). The firstly, i make LMDB sample rate 8000. Then i modify DeepspeechModel.lua, rnnInputsize= 1*81. I still change rnnInputSize !

conv:add(nn.SpatialConvolution(1, 32, 11, 41, 2, 2)) conv:add(nn.SpatialBatchNormalization(32)) conv:add(nn.Clamp(0, 20)) conv:add(nn.SpatialConvolution(32, 32, 11, 21, 2, 1)) conv:add(nn.SpatialBatchNormalization(32)) conv:add(nn.Clamp(0, 20))

I dont understand this code, why nInputPlane=1, etc... I dont know to modify SpatialConvolution and rnnInputSize .

SeanNaren commented 7 years ago

What is the size of the shortest clip? Could you make sure its above 0.5 seconds long? Otherwise it might not be large enough to go through the convolutional layers.

stephenvxx commented 6 years ago

@SeanNaren I cut all my wav above 1.0 seconds, but it is not change. Is a bug of cuda r5 ?

SeanNaren commented 6 years ago

Any chance this could help figure it out? https://github.com/SeanNaren/deepspeech.torch/issues/62#issuecomment-255733363

stephenvxx commented 6 years ago

Sometimes, i cut my wav files above 1.0 seconds (5000 files). The Bug error message is on #62 and i fix it. When i use all my audio files (1 Million Files) not successfully.