neural_sp
neural_sp copied to clipboard
hirofumi0810
End-to-end ASR/LM implementation with PyTorch
I trained model on Aishell corpus, and I found a error in train log: NaN or Inf found in input tensor. So, how dose it come about? How does it...
Hello, does Transformer have not implemented beam_search_chunk_sync yet? So how does MMA test?
run.sh: line 186: 9762 Segmentation fault (core dumped) CUDA_VISIBLE_DEVICES=${gpu} ${NEURALSP_ROOT}/neural_sp/bin/asr/train.py --corpus aishell1 --config ${conf} --config2 ${conf2} --n_gpus ${n_gpus} --cudnn_benchmark ${benchmark} --train_set ${data}/dataset/${train_set}.tsv --dev_set ${data}/dataset/${dev_set}.tsv --eval_sets ${data}/dataset/${test_set}.tsv --unit ${unit} --dict ${dict}...
The model [https://arxiv.org/pdf/2005.09394.pdf](url) , But the ''decode_streaming'' in speech2text.py did not support the streamming transformer? It only support rnn model?
``` 76 [1:12:36 1 else []) File "neural_sp/neural_sp/models/seq2seq/speech2text.py", line 741, in decode ensmbl_eouts, ensmbl_elens, ensmbl_decs) File "neural_sp/neural_sp/models/seq2seq/decoders/transformer.py", line 883, in beam_search rightmost_frame = max(0, aws_last_success[0, :, 0].nonzero()[:, -1].max().item()) + 1...
`Error in `conv2Lblstm512H5L_sumfwdbwd_chunkL-1R40_drop4_lstm_transducer1024H2L_adam_lr0.001_bs4_accum8_ctc0.3_2': double free or corruption (fasttop): 0x000055de29c92210 ***`
I've got the following error message from stage 3 (training lm) during training librispeech model in the example directory. **AttributeError: 'numpy.ndarray' object has no attribute 'items'** Checking the corresponding code...
Hello ， I am using neural_sp to train aishell-1 and another task, but I find that when i use 4 GPU to train ASR model, it needs 8 hours per...
Hello! Thank you for making your code public. I hope to reproduce performance in the paper, but I failed to reproduce it several times (especially, librispeech). 1. Is hyperparameters used...
Metadata
Owner
Metadata
End-to-end ASR/LM implementation with PyTorch