-
**Describe the bug**
Running a basic fastconformer hybrid recipe fails with image `nemo:24.07` and newer; more specifically, the reported RNNT WER numbers are all over the place, whereas CTC WER numb…
-
I am try to use this implementation with apex half precision training, but it can't.
showing that it need float rather that half:
______________
File "/data/asr_v3/src/model/transformer_transduc…
-
### 🐛 Describe the bug
def loss(self,audio_feat,feat_lens,target,target_lens):
"""
audio_feat: mel_spectrogram,
feat_lens :mel_length before padding
targe…
-
CUDA_VISIBLE_DEVICES=6,7 python -m torch.distributed.launch --nproc_per_node 2 --master_port=29501 finetune.py
多卡finetune damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online 模型时报错:
Ta…
-
### 🚀 The feature
I’d like to propose the integration of tree-constrained pointer generator (TCPGen) [1] and Minimum Biasing Word Error (MBWE) training [2] for contextual biasing into torchaudio pack…
-
```
$ CUDA_VISIBLE_DEVICES=0 ctest --rerun-failed --output-on-failure
Test project /home/jtrmal/projects/k2/build_debug
Start 97: rnnt_loss_test_py
1/1 Test #97: rnnt_loss_test_py ...........…
-
Following is my code. I am running in colab, and i copied some of the code from online streaming asr using microphone.(https://github.com/NVIDIA/NeMo/blob/main/tutorials/asr/Online_ASR_Microphone_Dem…
-
Hi,
I've just ended a training of a conformer using the sentencepiece featurizer on LibriSpeech over 50 epochs.
Here are the results if you want to update your readme:
```
dataset_config:
t…
-
https://pytorch.org/blog/optimizing-cuda-rnn-with-torchscript/
samgd updated
4 years ago
-
I am getting a lot of deletions in my RNN-T training/decoding setup relative to Transformer/Conformer. The data is the "Malach" corpus; about 200 hours of English but accented speech from Holocaust su…