-
### 🚀 The feature, motivation and pitch
# Preface
Hello! I am trying to export the codes for audio preprocessing on `kaldi` module in torchaudio.
I have few feature requests:
- Is there any …
-
How can I compute fbank features identical to this (kaldi)?
https://github.com/thewh1teagle/ort-diarize/blob/main/extract.py#L6
-
So, I never think to distribute my many little scripts, but I have one you might appreciate that I just call `tcolors`:
```sh
#!/bin/sh
for style in "$@"; do # Dump colors to evaluate color combi…
-
Hi there,
I am wondering what does fbank really give us in the dataloader? I went to torchaudio doc and did not find much info about what it is. Does anyone have a link to its explanation?
Thank…
lix4 updated
5 months ago
-
同一个视频，在windows是好的，ubuntu上报错
RROR:root:An error occurred: choose a window size 400 that is [2, 160] | 0/24 [00:00
-
Traceback (most recent call last):
File "D:\ai\josencomfyui\ComfyUI\execution.py", line 313, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_bl…
-
Hi, I noticed that the fmax for fbank computation in cosyvoice.yaml is set to 8000Hz [fmax](https://github.com/FunAudioLLM/CosyVoice/blob/c901a12789e0a9d8cec54c3caf1bc304533bdf82/examples/libritts/cos…
-
## 🐛 Bug
The output of the fbank feature calculations differs from that of kaldi.
## To Reproduce
Steps to reproduce the behavior:
using the following or even the defaults parameters:
``…
-
When to extract the fbank feature, the fbank.cfg is not in conf dirs, so how can I get it?
-
please support batch kaldi fbank computation/
"waveform (Tensor) – Tensor of audio of size (c, n) where c is in the range [0,2)"
right now only single utt compute is support