-
First of all, thank you for making efforts to implement this paper.
Regarding the unsatifised experimental results, some possible implementation issues are identified to cause this performance gap.
…
-
```Julia
"""
D × T × B
"""
function fdtb(m::LAS{M}, Hs::DenseArray{R,3}, ψhs::Vector{M}, maxT::Integer = 8size(Hs,2))::Vector{M} where {R
-
Hi Eduardo,
What are your plans for this code? It is described as unfinished and has not been updated lately.
I am interested in working on this, and even more interested in code for this subseq…
-
I am trying to implement a model using the bayesian lstm layer given I already have a model that relies on lstm and it gets good results for a classification task.
When I use the bayesian layer the l…
-
@BrikerMan I want to say thank you for developing this library and providing incredible support along with it. Kudos to you!
I want to create a model that will predict labels given a translation an…
-
First of all, thank you for making such a great library!
I'm trying to implement some [chordify](https://chordify.net/) functionality for myself, and one of the things I'd like to be able to do is …
-
I'm trying to train a new voice using Merlin. But now, the generated voice doesn't sound very natural.
Could anyone kindly provide some hints about how I can improve the quality of the voice (e.g., w…
-
RuntimeError: cuda runtime error (59) : device-side assert triggered at /opt/conda/conda-bld/pytorch_1533672544752/work/aten/src/THC/generic/THCTensorCopy.cpp:70
/opt/conda/conda-bld/pytorch_153367…
yrj90 updated
5 years ago
-
SeacoParaformer参数设置(funasr==1.0.19)：
torchrun \
--nnodes 1 \
--nproc_per_node ${gpu_num} \
../../../funasr/bin/train.py \
++model="${model_name_or_model_dir}" \
++model_revision="${model_revisio…
-
环境安装：
```
python==3.8.3
torch==1.13.1+cu117
funasr==1.0.0
```
使用模型：
`[https://www.modelscope.cn/models/damo/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary](url…