eesen

eesen copied to clipboard

Librispeech - Training starting error

3

Hi, it stops after this message: [NOTE] TOKEN_ACCURACY refers to token accuracy, i.e., (1.0 - token_error_rate). EPOCH 1 RUNNING ... TAG: 10_1.0 lrate 4e-05, Brief error: ERROR (train-ctc-parallel:AddVecToRows():cuda-matrix.cc:541) cudaError_t 48...

omprakashsonie

Hello community, Just wanted to ask if the resulting TLG.fst transducer should always be determinizable? I can see how we can ensure determinizability of LG.fst by adding disambiguation symbols, but...

oleksii-a

hi,alls I already install essen and I am trying to run the aishell, but I got the failed: train-ctc-parallel --report-step=160 --num-sequence=16 --frame-limit=1200 --learn-rate=0.003 --momentum=0.9 --verbose=1 'ark,s,cs:apply-cmvn --norm-vars=true --utt2spk=ark:data/train_nodev/utt2spk scp:data/train_nodev/cmvn.scp scp:exp/train_char_l5_c512/train.scp...

icestoneking

Error when training Librispeech recipe

2

Hi Alls I already install essen and I want to try to run the librispeech recipe. I got an error: `EPOCH 1 RUNNING ... TAG: 10_1.0 lrate 4e-05, steps/train_ctc_parallel_mult.sh: line...

z430

Installing error

8

I am installing one year ago version of essen with cuda 7.5 and cuda8.0 on a ubuntu with GPU. Got following error during install: "gcc: error trying to exec 'cc1plus':...

hdubey

Training Error when run tedlium recipe

2

Hi Alls: I already install essen and I am trying to run the tedlium recipe, but I got the error: train-ctc-parallel --report-step=1000 --num-sequence=20 --frame-limit=25000 --learn-rate=0.00004 --momentum=0.9 --verbose=1 'ark,s,cs:apply-cmvn --norm-vars=true --utt2spk=ark:data/train_tr95/utt2spk...

yuexianghubit

Faster kaldi io

4

siddalmia

Questions about tf_clean branch

17

Hi all, I've seen the new tf_clean branch is available, so be trying to use it. I'm using ```swbd/v1-tf``` recipe and was able to train it successfully. However, I cannot...

jinserk

Error Decoding : Tedlium example

7

Hi, I'm trying to run Tedlium example with LSTM & CTC on phonemes. The training work well when running run_ctc_phn.sh but for decoding step, I have this error : decode_dev/log/decode.1.log...

aheba

Difference between decode-faster vs. latgen-faster

4

Hi, I try do decode the output of an acoustic model (CTC) built in pytorch with the eesen framework. On WSJ, I achieve good results with the `decode-faster` function as...

stefbraun