19 questions
0
votes
0
answers
529
views
Use whisperx and pyannote in Colab without HuggingFace token
Hello Stack Overflow Community! I would like to use WhisperX and Pyannote as described on this GitHub to combine automatic transcription and diarization. I can do it on Colab using the Huggingface (HF)...
1
vote
0
answers
371
views
Whisper and pyannote 3.1 : AttributeError: 'list' object has no attribute 'get'
I'm using this script to diarize then transcribe speach using pyannote.audio and whisper. Using pyannote 2.1, it works perfectly, but then, when I change the version used to the latest (3.1), I get ...
- 89
1
vote
1
answer
154
views
Azure Speech diarization failing to tag speakers properly until a long 7second statement is spoken
Azure speech private preview for diarization was earlier setting “unknown” speaker tag until it recognise a long 7 seconds statement from a speaker, with the api in public preview it started tagging ...
- 49
0
votes
1
answer
344
views
Google Speech-to-Text API Speaker Diarization with Python .long_running_recognize() method
I was following the answer in this question. But my audio is more then 1 min so I have to use .long_running_recognize(config, audio) method instead .recognize(config, audio). Here is the code:
from ...
- 441
0
votes
0
answers
840
views
Azure speech-to-text speaker identification (or diarization): no text and no guests
I run this sample code from here, just changing the file name and the number of channels from eight to two (one channel is not supported).
My goal is to test the speaker identification. Actually the ...
- 137
0
votes
1
answer
75
views
Google Speech to text APIs returns only one side of the conversation
I am using Google APIs speech-to-text to transcript audio files (wav files) that are stored in GCS bucket. The audio files are phone records and have 3 speakers ( IVR, Customer, and Engineer) and the ...
1
vote
3
answers
4k
views
Diart (torchaudio) on Windows x64 results in torchaudio error "ImportError: FFmpeg libraries are not found. Please install FFmpeg."
I am giving a try to a speech diarization project named diart
(based on hugging face models)
I follow the instructions using a miniconda environment which are essentially:
conda create -n diart python=...
- 3,321
1
vote
1
answer
2k
views
Segmention instead of diarization for speaker count estimation
I'm using diarization of pyannote to determine the number of speakers in an audio, where number of speakers cannot be predetermined. Here is the code to determine speaker count by diarization:
from ...
- 69
5
votes
1
answer
4k
views
Efficient speaker diarization
I am running a VM instance on google cloud. My goal is to apply speaker diarization to several .wav files stored on cloud buckets.
I have tried the following alternatives with the subsequent problems:
...
- 318
1
vote
0
answers
426
views
Extracting voice of different speakers in overlapping speech using pyannote
I am using Pyannote for speaker diarization. I am able to get the overlapping speech's start and end time but not able to do voice separation. Is there a way to use Pyannote for voice separation?
If ...
- 95
0
votes
1
answer
426
views
Can speech diarization be be integrated with deepspeech?
In an online meeting such as Google Meet/ Zoom, I want to detect change of speaker and then transcribe the audio for different speakers.
I am using Deepspeech model for speech to text. I have fine-...
- 95
1
vote
1
answer
625
views
AttributeError: 'NoneType' object has no attribute 'items' in pyannote speaker diarization package
When working with the pyannote python package from GitHub (tutorial link -> https://github.com/pyannote/pyannote-audio/blob/develop/tutorials/voice_activity_detection.ipynb)
I receive the following ...
- 11
2
votes
1
answer
3k
views
How can I count the number of people speaks in an audio file
I'm working on an audio project. My goal is to count the number of people who spokes in an audio file. We can consider that we already removed the noise from that audio.(for example, if there are two ...
0
votes
0
answers
537
views
How to split 1 channel audio into 2 channels?
I have an audio file with two speakers on 1 channel. I would like to separate the audio in 2 channels (one per speaker).
I was thinking of splitting on silences, or more complicated things like ...
- 1
0
votes
1
answer
4k
views
Speaker diarization model in Python
I’m looking for a model (in Python) to speaker diarization (or both speaker diarization and speech recognition). I tried with pyannote and resemblyzer libraries but they dont work with my data (dont ...
- 1
0
votes
1
answer
1k
views
speaker diarization for telephone conversations using Resemblyzer
I have audio recordings of telephone conversations,
I used Resemblyzer it clusters audio based on speakers. the output is labelling, which is basically a dictionary of which person spoke when (...
1
vote
1
answer
516
views
torch.hub.load('pyannote/pyannote-audio', 'dia') doesn't work in local
I was using this code in google colab but it doesn't work when I want to use it in local
OWN_FILE = {'audio': 'file.wav'}
pipeline = torch.hub.load('pyannote/pyannote-audio', 'dia')
diarization = ...
0
votes
2
answers
235
views
Python: How to align two lists using start/end timestamps in the item
I have two lists, each sorted by start_time and that the end_time does not overlap with other items:
# (word, start_time, end_time)
words = [('i', 5.12, 5.23),
('like', 5.24, 5.36),
(...
- 183
2
votes
0
answers
1k
views
Speaker Diarization using Resemblyzer
I am new to Speaker Diarization and was exploring Resemblyzer library and have a few questions. I looked at the diarization demo here: demo02_diarization.py
Use live audio stream instead of static ...
- 6,241