Issues
- 3
- 3
MAC M3 audio backend no longer appearing
#3785 opened by tval2 - 2
- 4
Random cropping for variable length sequences
#3704 opened by ATriantafyllopoulos - 0
RTSP with StreamReader
#3797 opened by pedromoraesh - 0
StreamRead failing when Reading RTSP stream with CPU
#3798 opened by pedromoraesh - 0
How to use my finetuned version of wave2vec2 for forced alignment as shown in example/
#3796 opened by omerarshad - 2
Torchaudio is not detecting FFmpeg
#3789 opened by ruliworst - 0
Packet passthrough support
#3795 opened by materight - 0
Real time synthesis with oscillator_bank
#3788 opened by peastman - 0
Failed to open output "-" (Invalid argument).
#3784 opened by liuliujiang - 1
Can not load commonvoice dataset on windows
#3781 opened by jacobjennings - 0
frame offset + num frames to utilize http range header
#3783 opened by mogwai - 2
torchaudio/lib/libtorchaudio_sox.so, 0x0006): Library not loaded: @rpath/libsox.dylib
#3724 opened by luohao123 - 0
- 1
Cannot load audio from pathlib.Path
#3775 opened by roedoejet - 0
- 0
Using MMS model with `star` token for batch size > 1
#3772 opened by huangruizhe - 1
librispeech_conformer_rnnt example gives error: "AttributeError: 'tuple' object has no attribute 'targets'"
#3707 opened by kikofmas - 0
- 1
cherry-picks for 2.3
#3768 opened by ahmadsharif1 - 0
Windows CI is broken
#3767 opened by ahmadsharif1 - 3
- 0
torchaudio.load not loading all the frames
#3762 opened by ashinkajay - 2
- 0
torchaudio load opus failed
#3753 opened by Mddct - 0
Installation with pip git+ is broken
#3752 opened by gdagil - 6
I have some questions about RNNT loss.
#3750 opened by girlsending0 - 1
Fail to align numbers
#3713 opened by amorin-gladia - 1
Bug in error message in forced alignment
#3747 opened by zmolikova - 0
how to install libtorchaudio for cpp project ?
#3746 opened by mullerhai - 1
torchaudio.functional.convolve with torch.complex32 and interleaved fake complex torch.bfloat16
#3739 opened by pfeatherstone - 0
- 1
- 2
specify fmin and fmax for Spectrogram
#3732 opened by bilzard - 5
Resampling at arbitrary time steps
#3725 opened by pfeatherstone - 0
`torchaudio.info` returns incorrect result for `num_frames` when input is a video
#3731 opened by lematt1991 - 0
Vol silently clamps outputs to range [-1,1]
#3730 opened by CookiePPP - 0
torchaudio.compliance.kaldi requires annotation on vtln_warp_mel_freq
#3729 opened by giacomopiccinini - 1
streamreader add_video_stream doesn't seem to accept any filter_desc options
#3719 opened by caspersmit-sa - 0
Can't install some of the libraries
#3720 opened by Toplica001 - 0
- 2
torchaudio need to save segmented chunks as opus like here: torchaudio.save( ..format = 'opus',..
#3714 opened by npovey - 3
The ffmpeg integration shouldn't download linux binaries when the UNIX cmake variable is defined - it should issue proper messages for non-Linux UNIX systems
#3716 opened by yurivict - 1
Torchaudio.load() reference not found in Pycharm
#3715 opened by asusdisciple - 1
WLS2 compatibilty issue
#3712 opened by arnodelorme - 0
_pickle.UnpicklingError: invalid load key, 'v'.
#3711 opened by YuQing2000 - 2
- 1
Failed to open the input "Resampled Audio Data_16kHz/Resampled Audio Data_16kHz/data10/data10.wav" (No such file or directory).
#3706 opened by yalcincenik - 0
torchaudio build not working
#3703 opened by jdgh000