Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

update whisper notebook #127

Merged
merged 1 commit into from
May 16, 2024
Merged

update whisper notebook #127

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
46 changes: 43 additions & 3 deletions playbooks/roles/whisper/files/whisper_template.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -185,9 +185,7 @@
"\n",
"Step 1: create a token [here](https://huggingface.co/settings/tokens)\n",
"\n",
"Step 2: Enter your token in the code cell below and run it. If you haven't accepted the terms earlier, you will get an error message with a link to accept the terms for the relevant model (Segmentation , Voice Activity Detection (VAD), and Speaker Diarization), follow the link and accept the terms and rerun the code cell below. You should now get another error with a new link. Repeat the process until you have accepted the terms for all models actually get output instead of an error message. \n",
"\n",
"Use step 7 to save the diarized transcript in all file formats (make sure to change the na)."
"Step 2: Enter your token in the code cell below and run it. If you haven't accepted the terms earlier, you will get an error message with a link to accept the terms for the relevant model (Segmentation , Voice Activity Detection (VAD), and Speaker Diarization), follow the link and accept the terms and rerun the code cell below. You should now get another error with a new link. Repeat the process until you have accepted the terms for all models actually get output instead of an error message. \n"
]
},
{
Expand All @@ -210,6 +208,48 @@
"print(diarized_transcript[\"segments\"]) # segments are now assigned speaker IDs"
]
},
{
"cell_type": "markdown",
"id": "f75b1f38-9662-43d3-8f27-aa8310d60d80",
"metadata": {},
"source": [
"## Save diarized transcripts\n",
"\n",
"Run the cell below to save the diarized transcript in `.json` and `.txt` format"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a46eaa00-b24c-4506-9f5e-5da0dff1b48d",
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"import os\n",
"\n",
"output_directory = project_folder + \"/output/diarized_transcripts\"\n",
"\n",
"if not os.path.isdir(output_directory):\n",
" os.makedirs(output_directory)\n",
" \n",
"writer = whisper.utils.get_writer(\"json\", output_directory)\n",
"writer(diarized_transcript, audio_file, writer_options)\n",
"\n",
"import pandas as pd\n",
"import json\n",
"\n",
"file_no_ext = os.path.splitext(os.path.basename(audio_file))[0] \n",
"json_filename = file_no_ext + \".json\"\n",
"\n",
"with open(output_directory + json_filename) as json_file:\n",
" data = json.load(json_file)\n",
"\n",
"df = pd.DataFrame.from_dict(data[\"segments\"], orient='columns')\n",
"df.to_csv(output_directory + file_no_ext+ '.txt', header=None, index=None, sep=';', mode='a')"
]
},
{
"cell_type": "markdown",
"id": "917876a6",
Expand Down
Loading