joan126

which am is used in kaldi ?

2

Hi, I am using MFA for force alignment between phonenes and audio, I want to know nnet3 or chain model is used to train MFA from scarch? As I know...

tensorrt use onnx_parser to parse onnx file error

1

## Description error occured when use tensorrt to build engine with onnx model file using onnx_parser . onnx model from tensorflow-gpu 1.14.0 ## Environment **TensorRT Version**: 8.2.3 **ONNX-TensorRT Version /...

Assertion failed: axesInput.allValuesKnown() && "Axes input for unsqueeze operation should be a constant tensor."

2

when using onnx2trt to convert onnx model to trt engine, an error occurs : Assertion failed: axesInput.allValuesKnown() && "Axes input for unsqueeze operation should be a constant tensor." testing environment...

teacher-forcing

1

have you tried teacher forcing rate set to 1.0 during training cotatron ?

[BUG]: start titan example too slow

6

### 🐛 Describe the bug when run titan demo on 3090 x 8 gpu , it start too slow in about 2- minutes; GPU 100% usage; pipeline=4; tp=2; ### Environment...

你好，在论文中了解到训练数据是中，英文按照通能比例训练的LLM模型，中文数据中有用到悟道的数据1.2T, 请问这里面的悟道数据包含了180G的对话数据了吗？ 谢谢~

Hello, I want to finetune only last k layer of GPT model. how can I solve this?

tacotron2整合版本有什么特别之处？

1

请问，这个整合了nvidia t2和Ry t2的Tacotron2版本建模效果比Ry的tf版本有提升吗？