-
hi,
I have a problem with recognition oov in ASR (like proper noun) and it's not appear in training set. I have read about wfst +rnn transducer in paper of google [streaming end to end speech recogn…
-
### System information
- **Have I written custom code**: Yes
- **OS Platform and Distribution (e.g., Linux Ubuntu 16.04)**: Linux Ubuntu 18.04.2 LTS
- **TensorFlow installed from (source or binary)…
-
Hi, I'm trying to train conformer for the Lithuanian language.
I'm training on `NVIDIA Tesla P100` and I keep getting OOM after some time.
Using all default values from `examples/conformer/confi…
-
@hirofumi0810
hi, author, i train a model with transducer configuration, it's failed while processing batch_dev, the code is as follow:
batch_dev = iter(dev_set).next(batch_size=1 if 'transducer' i…
-
Hello,
I'm training an ASR Transformer model for Librispeech but I'm not getting acceptable results (not converging at all after some epochs). I'm using pytorch.distributed.launch.
I'm using a…
-
Not sure if this is the correct place to ask this question, so I apologize in advance if I have broken protocol :-P
Does Mycodo have built-in support for I2C or SPI controlled digital potentiometer…
-
Traceback (most recent call last):
File "/home/yangweiming/MUSIC/Speech_Recognition/Kospeech/bin/main.py", line 175, in main
last_model_checkpoint = train(config)
File "/home/yangweiming/MU…
-
Environment: google cloud instance, debian10, tf2.3, cuda11, 4x tesla t4
Model: conformer, training with train_ga_subword_conformer.py
Config: batch size=4, ga=1, others are the same as given one, t…
ghost updated
3 years ago
-
Hello I am facing an error while testing the Context-Net model. Here are the exact steps which I followed.
1) Forked repository and downloaded the datasets from librispeech. `https://www.openslr…
-
The LibriSpeech transducer ASR recipe fails to run with CPU only, i.e.
python train.py hparams/train.yaml --device=cpu
While loading the HyperYaml configurations file
it looks for a CUDA driver.
…