Comments (9)
You'll need a backend for librosa. See this thread: librosa/librosa#219 (comment)
from resemblyzer.
Still struggling... :
(base) (Resemblyzer) marco@pc:~/Resemblyzer$ python3 demo02_diarization.py
Traceback (most recent call last):
File "demo02_diarization.py", line 2, in <module>
from demo_utils import *
File "/home/marco/Resemblyzer/demo_utils.py", line 1, in <module>
from mpl_toolkits.axes_grid1 import make_axes_locatable
ModuleNotFoundError: No module named 'mpl_toolkits'
(base) (Resemblyzer) marco@pc:~/Resemblyzer$ python3 demo02_diarization.py
Traceback (most recent call last):
File "demo02_diarization.py", line 2, in <module>
from demo_utils import *
File "/home/marco/Resemblyzer/demo_utils.py", line 1, in <module>
from mpl_toolkits.axes_grid1 import make_axes_locatable
ModuleNotFoundError: No module named 'mpl_toolkits'
(base) (Resemblyzer) marco@pc:~/Resemblyzer$ pip3 install mpl_toolkits
Collecting mpl_toolkits
ERROR: Could not find a version that satisfies the requirement mpl_toolkits (from versions: none)
ERROR: No matching distribution found for mpl_toolkits
(base) (Resemblyzer) marco@pc:~/Resemblyzer$
(base) (Resemblyzer) marco@pc:~/Resemblyzer$ conda install -c conda-forge mpl_toolkits
Collecting package metadata (current_repodata.json): done
Solving environment: failed with initial frozen solve. Retrying with flexible solve.
Collecting package metadata (repodata.json): done
Solving environment: failed with initial frozen solve. Retrying with flexible solve.
PackagesNotFoundError: The following packages are not available from current channels:
- mpl_toolkits
Current channels:
- https://conda.anaconda.org/conda-forge/linux-64
- https://conda.anaconda.org/conda-forge/noarch
- https://repo.anaconda.com/pkgs/main/linux-64
- https://repo.anaconda.com/pkgs/main/noarch
- https://repo.anaconda.com/pkgs/r/linux-64
- https://repo.anaconda.com/pkgs/r/noarch
To search for alternate channels that may provide the conda package you're looking for, navigate to
https://anaconda.org
and use the search bar at the top of the page.
from resemblyzer.
Thank you for reporting that, I believe this is due to your matplotlib version mismatching mine. I have 3.1.1, what is yours (pip freeze | grep matplotlib
)?
from resemblyzer.
Solved that problem by installing matplotlib (version 3.1.1) (I discovered it was not installed).
But now got new issue:
(Resemblyzer) marco@pc:~/Resemblyzer$ python3 demo02_diarization.py
Traceback (most recent call last):
File "/home/marco/Resemblyzer/Resemblyzer/lib/python3.7/site-packages/librosa
/core/audio.py", line 127, in load
with sf.SoundFile(path) as sf_desc:
File "/home/marco/Resemblyzer/Resemblyzer/lib/python3.7/site-packages/soundfile.py", line
627, in __init__
self._file = self._open(file, mode_int, closefd)
File "/home/marco/Resemblyzer/Resemblyzer/lib/python3.7/site-packages/soundfile.py", line
1182, in _open
"Error opening {0!r}: ".format(self.name))
File "/home/marco/Resemblyzer/Resemblyzer/lib/python3.7/site-packages/soundfile.py", line
1355, in _error_check
raise RuntimeError(prefix + _ffi.string(err_str).decode('utf-8', 'replace'))
RuntimeError: Error opening 'audio_data/X2zqiX6yL3I.mp3': File contains data in an unknown
format.
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "demo02_diarization.py", line 14, in <module>
wav = preprocess_wav(wav_fpath)
File "/home/marco/Resemblyzer/resemblyzer/audio.py", line 27, in preprocess_wav
wav, source_sr = librosa.load(fpath_or_wav, sr=None)
File "/home/marco/Resemblyzer/Resemblyzer/lib/python3.7/site-packages/librosa
/core/audio.py", line 142, in load
y, sr_native = __audioread_load(path, offset, duration, dtype)
File "/home/marco/Resemblyzer/Resemblyzer/lib/python3.7/site-packages/librosa
/core/audio.py", line 164, in __audioread_load
with audioread.audio_open(path) as input_file:
File "/home/marco/Resemblyzer/Resemblyzer/lib/python3.7/site-packages/audioread
/__init__.py", line 116, in audio_open
raise NoBackendError()
audioread.exceptions.NoBackendError
from resemblyzer.
You still need to install a backend
from resemblyzer.
(Resemblyzer) (base) marco@pc:~/Resemblyzer$ conda install -c conda-forge audioread
Collecting package metadata (current_repodata.json): done
Solving environment: done
# All requested packages already installed.
(base) (Resemblyzer) marco@pc:~/Resemblyzer$ python3 demo02_diarization.py
Loaded the voice encoder model on cpu in 0.06 seconds.
Running the continuous embedding on cpu, this might take a while...
Traceback (most recent call last):
File "demo02_diarization.py", line 42, in <module>
interactive_diarization(similarity_dict, wav, wav_splits)
File "/home/marco/Resemblyzer/demo_utils.py", line 171, in interactive_diarization
play_wav(wav, blocking=False)
File "/home/marco/Resemblyzer/demo_utils.py", line 35, in play_wav
sd.play(wav, sampling_rate, blocking=blocking)
File "/home/marco/Resemblyzer/Resemblyzer/lib/python3.7/site-packages/sounddevice.py", line
154, in play
**kwargs)
File "/home/marco/Resemblyzer/Resemblyzer/lib/python3.7/site-packages/sounddevice.py", line
2417, in start_stream
**kwargs)
File "/home/marco/Resemblyzer/Resemblyzer/lib/python3.7/site-packages/sounddevice.py", line
1374, in __init__
**_remove_self(locals()))
File "/home/marco/Resemblyzer/Resemblyzer/lib/python3.7/site-packages/sounddevice.py", line
697, in __init__
extra_settings, samplerate)
File "/home/marco/Resemblyzer/Resemblyzer/lib/python3.7/site-packages/sounddevice.py", line
2490, in _get_stream_parameters
info = query_devices(device)
File "/home/marco/Resemblyzer/Resemblyzer/lib/python3.7/site-packages/sounddevice.py", line
488, in query_devices
raise PortAudioError('Error querying device {0}'.format(device))
sounddevice.PortAudioError: Error querying device -1
from resemblyzer.
Good catch, you will either need to put an audio output device or disable the calls to sd.play
in demo_utils
. I'll fix that later
from resemblyzer.
With cdd51df, you should now be fine. It should only print an error when trying to play the audio but the program should work.
from resemblyzer.
I solve it by install ffmpeg on ubuntu18.04: sudo apt install ffmpeg.
from resemblyzer.
Related Issues (20)
- End-to-end trainable model HERE
- Async and parallel processing
- After diarization, The timestamps I got are irrelevants from original file HOT 3
- The Ability of Speaker Diarization with More Than 2 Speakers HOT 3
- Speaker Verification HOT 2
- Error while trying to plot speaker similarity in Resemblyzer
- Diarization Graph Issue HOT 1
- About pre-trained model HOT 2
- How to get time stamps for every speaker change?
- MATPLOTLIB FIGURES NOT DISPLAYING..How to solve this please help.. HOT 2
- New release plans to include latest changes? HOT 5
- Error while using Resemblyzer HOT 2
- Getting different speaker embeddings from same wav file on different machine HOT 2
- Speech Diarization
- Using VoiceEncoder as loss with time domain models
- AttributeError: module 'numpy' has no attribute 'bool'.
- What license does resemblyzer fall under? HOT 1
- RuntimeError: cuDNN error: CUDNN_STATUS_VERSION_MISMATCH
- is this speaker embedding better than X-vector?
- Demo2 not showing any result HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from resemblyzer.