-
Hi @breizhn ,
I'm trying train stateful DTLN model. And I see `time_dat = Input(batch_shape=(1, self.blockLen))` .
Why is the `self.batchsize = 1` ? Is this performance better?
-
Hi to all,
I think there is a problem in the class definition of the model for 2 reasons.
First, i can load the classical model.h5 but not the DTLN_norm_500h.h5
when I want to use the 500h model …
-
Hi, Nils, after carefully reading the [paper](https://arxiv.org/pdf/2010.14337.pdf) and the code in 'DTLN' project, I modified the model of DTLN to DTLN-aec's.I check the model structure again and aga…
-
您好，我看op支持文档上，onnx支持lstm转换，实际在转带lstm的模型时，发现段错误，原始模型为降噪模型DTLN模型，模型结构及原始模型如下：
![06A7210C2…
-
model = tf.saved_model.load('./pretrained_model/dtln_saved_model')
infer = model.signatures["serving_default"]
out_block= infer(tf.constant(in_block))['conv1d_1']
不知道这个[conv1d_1]转到paddle以后怎么推理
AIHHU updated
2 years ago
-
Hello,
I am trying to learn about quantization so was playing with a github repo trying to quantize it into int8 format. I have used the following code to quantize the model.
```
modelClass = D…
-
Hi. Recently, I tried to compile a pre-trained speech enhancement model on your website Cainvas (Model: DTLN https://github.com/breizhn/DTLN#real-time-processing-with-the-savedmodel-format). However, …
-
Hi,
I want to use tflite model in android project. When I load model to android studio it generates a code like below:
`
val model = Dtln.newInstance(context)
// Creates inputs for reference.
…
-
Nils is it possible to create an integer only models so this could run on accelerators or frameworks such as ArmNN?
https://www.tensorflow.org/lite/performance/post_training_quantization#full_integer…
-
> INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
> Traceback (most recent call last):
> File "real_time_processing_tf_lite.py", line 69, in
> interpreter_1.set_tensor(input_details_…