-
**Describe the bug**
TypeError: unsupported operand type(s) for +: 'Tensor' and 'list', occurs when wanting to extract the confidence levels for the STT FastConformer model.
**Steps/Code to rep…
-
Hi @titu1994,
Following our discussion in [this thread](https://github.com/NVIDIA/NeMo/discussions/7010#discussioncomment-9736124), I’m training a cache-aware FastConformer hybrid CTC-RNNT model fo…
-
**Describe the bug**
我们使用wenet中实现的bestrq代码，试图复现预训练模型的结果，但是效果不好，完全达不到论文中的WER结果。
**To Reproduce**
1. 我们使用librispeech 960h数据进行预训练模型训练，使用10h和100h的数据进行微调。
2. 我们仿照wav2vec2的实验设置，预训练模型接CTC，而不是bestrq论文中的…
-
**Describe the bug**
When I tried to generate timestamp with model: nvidia/parakeet-tdt-1.1b, I got following error,
ValueError: `char_offsets`: [{'char': [tensor(607, dtype=torch.int32)], 'start_…
-
after I build contaner, and enter it, when I preprocess the data, it have failure with data attribute.
```
root@ed1902ed9916:/workspace/rnnt# bash scripts/preprocess_librispeech.sh
Traceback (m…
-
### 问题描述 Issue Description
编译指令：
`cmake .. -DPY_VERSION=3.7 -DPYTHON_EXECUTABLE='which python3' -DWITH_XPU=ON -DON_INFER=ON -DWITH_TESTING=OFF -DWITH_XBYAK=OFF -DWITH_ARM=ON -DWITH_AARCH64=ON -DCMAK…
czp97 updated
3 months ago
-
Hi,
I'm currently trying to train a transducer model using rf. I use the `torch_amp="bfloat16"` option from previous setups. In the predictor I use a `rf.LayerNorm` followed by `rf.LSTM`. I think thi…
-
I have an Orin developer Kit and followed the instructions to run mlcommons inference 2.0 on it.
Orin is set to MAXN power mode.
The reported resnet50 throughput is 6,138.84fps in offline while …
-
命令为：
python ./wenet/bin/export_jit.py
--config /home/lsj/zdb/biye/wenet/examples/aishell/rnnt/exp/baseline/train.yaml
--checkpoint /home/lsj/zdb/biye/wenet/examples/aishell/rnnt/exp/baseline/avg_…
-
hi, thank you developed this great toolkit and open source.but i have some problem and cant solve by myself.
i run train.py in examples/conforme.After 20 epoches, loss reduce to 6.92。 but i get non…