-
What do I need to do to get the TTS to run in realtime? I've attached the python file I'm using to get the output. It takes about 15 seconds until it prompts the user for the text input. Then takes ab…
-
Hi, I want to use tensorflow-serving to deploy the fastspeech2 model. I successfully converted the model to saved_model format and used the tf.saved_model.load() API to verify that the model can be ca…
-
Have you tried full integer quantization? I successfully converted the fastspeech2 lite model using full integer quantization, but a core dump occurred during inference. Can you give me some suggestio…
-
Hi,
So I converted Fastspeech2 model to TFlite, when I tried to inference from TFlite I am getting this error
decoder_output_tflite, mel_output_tflite = infer(input_text)
interpreter.invoke()
F…
-
Hello, I would like to ask how to use C++ to load fastspeech2 tflite format model, can you recommend any examples?
-
I tried to train FastSpeech2 in other language. In that step using MFA to get alignment, i dont know how to apply for my language?
-
@alancucki
Read the paper, I got some early results in conditioning but the model is overfitting, I am wondering if thats because, in your paper you had mentioned that you used LJSpeech WITH two ext…
-
Hi,
Nowadays, I've been trying to train a fastspeech2 without a teacher model(Tacotron2).Just use the MFA.But I have some problem.
In this [issue](https://github.com/espnet/espnet/issues/2632#issu…
-
Hello, @Jackson-Kang,
While I was reviewing the codes, I realized that in evaluation.py, when it evaluates the model and calculates the loss, it uses the target data, not the predicted model.
T…
-
**Describe the bug**
Hi,
it's more an issue than a bug. We have two machines with 2x Titan RTX 24 GB GPU each. Do you see a way for us to train the Fastspeech2 Conformer model?
You specified, that…