Comments (5)
What do you mean by incoherent timestamps, could you be more specific, eg with example
from whisperx.
He might be talking about the not completed diarize option. As whisper itself is incredible good at timestamps and is basically a complete package (except of a few languages). As the diarize option does not take into account cross-talking speakers. I myself just doubled the audio files length by using Ffmpeg '-filter:a', 'atempo=0.5'
and the diarize accuracy is usually within 1 second to switch speakers and can switch between cross-talking people accurately within 3 seconds. So every small talk answers like 'yes' and 'no', will be under the speaker who asked the question instead of the person answering. Which makes sense, but could be fixed almost completely, because Whisper detects a new sentence by itself far better than Pyannote does. So just having one or two worded sentences be a completely new speaker and then you can manually search for the speaker and replace with the name and ofcourse in the end divide the time in the output file by 2 with something like the 'Datetime' package.
from whisperx.
Thank you both of you! It is about timestamps overlapping: segment B starts before segment A ends. I thought it was because of cross-talking too, I would understand the problem, but it is not. For example in the following example (from a .word.srt file):
62
00:00:37,316 --> 00:00:37,456
so
63
00:00:37,440 --> 00:00:37,500
so
64
00:00:38,745 --> 00:00:39,206
we
And the speaker doesn't repeat "so" at this particular moment (just a little pause).
from whisperx.
Btw running WhisperX with the commit ba102fe (see issue #49), I had much less timestamps incoherence (only 13 files, against 139 in current version).
from whisperx.
recent VAD filter push should hopefully handle this a582a59
from whisperx.
Related Issues (20)
- WhisperX crashes unexpectedly throughout usage HOT 4
- Feature Request: Using manual transcripts for subtitles
- How could I load the local model HOT 2
- Limit the length of my subtitles HOT 2
- A single word in one time stamp
- Error while --max_words_per_line 1
- Stuck on load_model() HOT 4
- [!] Error: 'language' when attempting to use srt_writer HOT 1
- long audio out of memory HOT 1
- Not found in colab HOT 1
- NameError: name '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' is not defined HOT 1
- Speaker diarization system in kazakh language.
- Can WhiperX load custom model from Huggingface ? HOT 1
- when load whisperx on aarch64 platform,occur error, whisperx must need torch version complied with cuda?
- 404 Client Error for speaker-embedding.onnx HOT 1
- Diarization before Transcription?
- I just can't make it SYNC any ideas would be helpful. hours on hours days after days and nothing.
- expose some more common args to the webui? HOT 1
- Arguments for repetition_penalty and no_repeat_ngram_size HOT 2
- Conflicting dependencies ERROR HOT 1
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 whisperx.