Mirroristas/whisper
2
0
Fork 0
mirror of https://github.com/openai/whisper.git synced 2025-03-30 14:28:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

Use ndimage.median_filter instead of signal.medfilter (#812)

Browse Source 
For a 30s long audio file which didn't have any silence, ndimage.median_filter took 7s where signa.medfilter took 30s.

Co-authored-by: Umar Farooqi <umar@paystash.com>
Co-authored-by: Jong Wook Kim <jongwook@nyu.edu>
This commit is contained in:
Umar Farooqi 2023-01-17 17:43:05 -05:00 committed by GitHub
parent a84191faae
commit f0083e7eb2
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
notebooks/Multilingual_ASR.ipynb
View File

@ -874,7 +874,7 @@
"from IPython.display import display, HTML\n",
"from whisper.tokenizer import get_tokenizer\n",
"from dtw import dtw\n",
"from scipy.signal import medfilt\n",
"from scipy.ndimage import median_filter\n",
"\n",
"%matplotlib inline\n",
"%config InlineBackend.figure_format = \"retina\""
@ -3610,7 +3610,7 @@
"\n",
" weights = torch.cat(QKs) # layers * heads * tokens * frames \n",
" weights = weights[:, :, :, : duration // AUDIO_SAMPLES_PER_TOKEN].cpu()\n",
" weights = medfilt(weights, (1, 1, 1, medfilt_width))\n",
" weights = median_filter(weights, (1, 1, 1, medfilt_width))\n",
" weights = torch.tensor(weights * qk_scale).softmax(dim=-1)\n",
" \n",
" w = weights / weights.norm(dim=-2, keepdim=True)\n",