bugbakery / bugbakery/transcribee
Identify speaker can fail
- Dominant language
- TypeScript
- Stars
- 515
- Forks
- 39
- Avg merge
- 19h 36m
- Merged PRs (30d)
- 15
Description
```
WARNING:root:Worker failed with exception
Traceback (most recent call last):
File "/nix/store/5akc6pb5xy7f1m08fhwvaj26wbnj5zq0-transcribee-worker/lib/python3.12/site-packages/transcribee_worker/worker.py", line 420, in run_task
task_result = await self.perform_task(task)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/nix/store/5akc6pb5xy7f1m08fhwvaj26wbnj5zq0-transcribee-worker/lib/python3.12/site-packages/transcribee_worker/worker.py", line 173, in perform_task
await self.identify_speakers(task, progress_callback)
File "/nix/store/5akc6pb5xy7f1m08fhwvaj26wbnj5zq0-transcribee-worker/lib/python3.12/site-packages/transcribee_worker/worker.py", line 231, in identify_speakers
await identify_speakers(
File "/nix/store/5akc6pb5xy7f1m08fhwvaj26wbnj5zq0-transcribee-worker/lib/python3.12/site-packages/transcribee_worker/identify_speakers.py", line 124, in identify_speakers
return await alist(aiter(async_task(work)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/nix/store/5akc6pb5xy7f1m08fhwvaj26wbnj5zq0-transcribee-worker/lib/python3.12/site-packages/transcribee_worker/util.py", line 63, in alist
return [item async for item in iterable]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/nix/store/5akc6pb5xy7f1m08fhwvaj26wbnj5zq0-transcribee-worker/lib/python3.12/site-packages/transcribee_worker/util.py", line 37, in async_task
value = fut.result()
^^^^^^^^^^^^
File "/nix/store/5akc6pb5xy7f1m08fhwvaj26wbnj5zq0-transcribee-worker/lib/python3.12/concurrent/futures/thread.py", line 59, in run
result = self.fn(*self.args, **self.kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/nix/store/5akc6pb5xy7f1m08fhwvaj26wbnj5zq0-transcribee-worker/lib/python3.12/site-packages/transcribee_worker/util.py", line 23, in _work_task
work_function(SubmissionQueue(loop, result_queue), *args, **kwargs)
File "/nix/store/5akc6pb5xy7f1m08fhwvaj26wbnj5zq0-transcribee-worker/lib/python3.12/site-packages/transcribee_worker/identify_speakers.py", line 112, in work
labels = clusterer.predict(np.vstack(embeddings))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/nix/store/5akc6pb5xy7f1m08fhwvaj26wbnj5zq0-transcribee-worker/lib/python3.12/site-packages/spectralcluster/spectral_clusterer.py", line 254, in predict
if fallback_clusterer.check_single_cluster(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/nix/store/5akc6pb5xy7f1m08fhwvaj26wbnj5zq0-transcribee-worker/lib/python3.12/site-packages/spectralcluster/fallback_clusterer.py", line 163, in check_single_cluster
raise ValueError(
ValueError: single_cluster_affinity_diagonal_offset must be significantly smaller than affinity matrix dimension
```
Ask me for a test document / file. (`Arsch v2.mp3`)
Contributor guide
Research direction
Reproduce the failure with the supplied test file, “Arsch v2.mp3”, and inspect transcribee_worker/identify_speakers.py around the clustering call shown in the traceback. Determine the expected behavior when speaker identification receives this input; done means the worker completes without the reported ValueError and produces speaker identification results.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- audio-video-rtc, machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 45/100