-
https://github.com/lovemefan/telespeech-asr-python/blob/c90966e55cb0fd4dd218c490d1335df60c876838/telespeechasr/onnx/onnx_infer.py#L207
samples *= 372768 ,这个值应该是32768吧?
-
**Description:** I intend to work on implementing the MFCC for feature extraction from audio signals. The MFCC is a popular technique for extracting features from audio signals such as voice or music,…
-
如果我用librosa 进行特征抽取
# --use-energy=false # use average of log energy, not energy.
# --sample-frequency=16000 # Switchboard is sampled at 8kHz
# --num-mel-bins=40 # similar to Google's setup.
…
-
**Describe the bug**
With (ipc3) testbench run the HiFi3 build and generic C version produce similar output. The HiFi4 build creates totally different output that looks wrong.
**To Reproduce**
…
-
用torchaudio替换librosa,使用项目数据集训练模型后,推理报错:RuntimeError: running_mean should contain 344 elements not 128
推理代码如下:
with torch.no_grad():
waveform, sample_rate = torchaudio.load("data/valid…
-
`!python beam.py -m experiments/es_en_20h -n 5 -k 5 -w 0.6 -s fisher_dev`
Generated the following error:
Beam for: experiments/es_en_20h gpu: 0
-------------------------------------------------…
imrnh updated
2 months ago
-
Using em++:
```
emcc (Emscripten gcc/clang-like replacement + linker emulating GNU ld) 3.1.61 (67fa4c16496b157a7fc3377afd69ee0445e8a6e3)
clang version 19.0.0git (https:/github.com/llvm/llvm-proje…
-
【问题】
按照项目描述操作,运行prepare_kaldi_feats.sh后没有生成.tsv 结尾的文件,请问这个文件怎么生成?
【项目描述如下】
1、利用kaldi提取40维mfcc特征,运行脚本参考prepare_kaldi_feats.sh
可将运行脚本prepare_kaldi_feats.sh与参数设置mfcc_hires.conf置于kaldi任一egs目录下(与cmd.…
ghost updated
1 month ago
-
Multi-frequency Cepstral Coefficients - a common set of speech features.
-
In the project there are a few mfcc variants. I am currently trying to get a result from the /Comirva/audio/mfcc.cs but the results of the processwindow is always zeroes. Does all of the code work and…