-
### System information
- Have I written custom code: Yes
- OS Platform and Distribution: 18.04.3 LTS Ubuntu
- TensorFlow installed : pre installed container
- TensorFlow version : 1.14.0
- Python…
-
Have I written custom code: N/A
OS Platform and Distribution: N/A
TensorFlow installed from: N/A
TensorFlow version: 1.8.0
Bazel version: N/A
CUDA/cuDNN version: 9.0/7.0
GPU model and memory: NV…
-
## 🐛 Bug
When I use a single GPU, all parameters in the model get non-zero gradients;
but after wrapping my model with nn.DataParallel, the gradients of some part (RNN in my case) of the model bec…
-
hi,
I just found my model can't be saved in BSON.
```julia
using Flux,BSON
model = Chain(Dense(12,12),LSTM(12,12),Dense(12,5))
Flux.@epochs 4 Flux.train!((x,y)->Flux.crossentropy(softmax(model(…
babaq updated
4 years ago
-
Hi,
Thanks for your great work of the online speech recognition.
I'm also insterested in the RNN-T baseline mentioned in the paper and would like to compare it with TDS model on my own training d…
-
Hello Eugene,
Thank you for sharing. Do you mind providing a pre trained model for faster training and benchmarking
Thanks in advance
-
Hi,
I have tried different model topologies and found it's really hard to converge.
I am reproducing results reported in papers ["_CAT: CRF-BASED ASR TOOLKIT_I" ](https://arxiv.org/pdf/1911.0874…
-
link: https://pdfs.semanticscholar.org/b0e7/58bd38511b13e2712ad3a013633af7fb682c.pdf
referenced from:
- https://twitter.com/forthshinji/status/986963950041423873
-
Hello, and thank you so much for this huge undertaking! I'm working on trying to convert Mozilla's DeepSpeech pre-trained model, and I get the error: "ValueError: Graph has cycles."
Any ideas about…
-
Is this the config for implementing MoChA - Monotonic Chunkwise Attention?
`2019-asr-local-attention/librispeech/local-heuristic.argmax.win02.exp3.ctc.config`