Troubleshooting of whisperX - Revision history

Planetoid: /* WhisperX Speaker Diarization Issue */

2026-09-10T05:34:47Z

WhisperX Speaker Diarization Issue

← Older revision		Revision as of 13:34, 10 September 2026
Line 24:		Line 24:
	=== WhisperX Speaker Diarization Issue ===		=== WhisperX Speaker Diarization Issue ===

	Problem: Speaker diarization failed on an interview transcript — over 500 segments were all labeled `SPEAKER_00`, even though it was clearly a two-person Q&A interview. The output looked like a single person talking.		'''Problem''': Speaker diarization failed on an interview transcript — over 500 segments were all labeled `SPEAKER_00`, even though it was clearly a two-person Q&A interview. The output looked like a single person talking.

	Solution		'''Solution'''
	Installed the new whisperx 3.8.6 (torch 2.8 cu126) in a venv. Diarization automatically switched to use the new-generation `pyannote/speaker-diarization-community-1` model.		Installed the new whisperx 3.8.6 (torch 2.8 cu126) in a venv. Diarization automatically switched to use the new-generation `pyannote/speaker-diarization-community-1` model.

	Version Info		'''Version Info'''
	Old environment: whisperX 3.1.1		Old environment: whisperX 3.1.1

Planetoid: /* Error: HF_TOKEN environment variable is not set */

2026-09-10T02:22:42Z

Error: HF_TOKEN environment variable is not set

@@ Line 20: / Line 20: @@
 # Enter <code>export HF_TOKEN='your Hugging Face token'</code>
 # Run bash command
 === Repeated Same Dialog Issue ===

Planetoid: /* whisperX Transcript File Format Guide */

2026-01-26T05:13:32Z

whisperX Transcript File Format Guide

← Older revision		Revision as of 13:13, 26 January 2026
Line 173:		Line 173:
	If using for the first time, it's recommended to directly open the srt format		If using for the first time, it's recommended to directly open the srt format

			== Further reading ==
			* [https://medium.com/@planetoid/how-to-add-punctuation-to-whisper-transcripts-using-ai-619362c9160c How to Add Punctuation to Whisper Transcripts Using AI \| Medium]

	[[Category: Generative AI]] [[Category: Software]] [[Category: Revised with LLMs]]		[[Category: Generative AI]] [[Category: Software]] [[Category: Revised with LLMs]]

Planetoid: /* WhisperX Audio Transcription Commands for Multiple Languages */

2025-09-01T10:34:25Z

WhisperX Audio Transcription Commands for Multiple Languages

← Older revision		Revision as of 18:34, 1 September 2025
Line 161:		Line 161:
	# fr = French		# fr = French

	Supported language codes can be found in the ~~Whisper tokenizer documentation at:~~ https://github.com/openai/whisper/blob/main/whisper/tokenizer.py		Supported language codes can be found in the [https://github.com/openai/whisper/blob/main/whisper/tokenizer.py Whisper tokenizer documentation] & [https://github.com/m-bain/whisperX/blob/main/EXAMPLES.md whisperX/EXAMPLES.md at main · m-bain/whisperX]

	== whisperX Transcript File Format Guide ==		== whisperX Transcript File Format Guide ==

Planetoid: /* WhisperX Audio Transcription Commands for Multiple Languages */

2025-09-01T10:30:00Z

WhisperX Audio Transcription Commands for Multiple Languages

← Older revision		Revision as of 18:30, 1 September 2025
Line 160:		Line 160:
	# es = Spanish		# es = Spanish
	# fr = French		# fr = French

			Supported language codes can be found in the Whisper tokenizer documentation at: https://github.com/openai/whisper/blob/main/whisper/tokenizer.py

	== whisperX Transcript File Format Guide ==		== whisperX Transcript File Format Guide ==

Planetoid: /* whisperX Troubleshooting Guide */

2025-09-01T10:26:45Z

whisperX Troubleshooting Guide

@@ Line 106: / Line 106: @@
 * '''Compatibility:''' Ensure that the versions of CUDA, cuDNN, and PyTorch are compatible with each other. Refer to the [https://pytorch.org/get-started/previous-versions/ PyTorch documentation] for version compatibility details.
 * '''Virtual Environments:''' If you’re using a virtual environment, make sure it has access to the system’s CUDA and cuDNN installations. You might need to install CUDA and cuDNN within the virtual environment or ensure that the environment variables are correctly set.
 == whisperX Transcript File Format Guide ==

Planetoid at 04:31, 28 August 2025

2025-08-28T04:31:30Z

@@ Line 106: / Line 106: @@
 * '''Compatibility:''' Ensure that the versions of CUDA, cuDNN, and PyTorch are compatible with each other. Refer to the [https://pytorch.org/get-started/previous-versions/ PyTorch documentation] for version compatibility details.
 * '''Virtual Environments:''' If you’re using a virtual environment, make sure it has access to the system’s CUDA and cuDNN installations. You might need to install CUDA and cuDNN within the virtual environment or ensure that the environment variables are correctly set.
 [[Category: Generative AI]] [[Category: Software]] [[Category: Revised with LLMs]]

Planetoid at 10:00, 11 August 2025

2025-08-11T10:00:55Z

← Older revision		Revision as of 18:00, 11 August 2025
Line 35:		Line 35:
	When running:		When running:

	<~~syntaxhighlight~~ lang="bash">$ whisperx input.mp3 --model large-v2 --diarize --highlight_words True</~~syntaxhighlight~~>		<pre lang="bash">$ whisperx input.mp3 --model large-v2 --diarize --highlight_words True</pre>
	You encounter a long error trace ending with:		You encounter a long error trace ending with:

Line 53:		Line 53:
	<ul>		<ul>
	<li><p>Check if cuDNN is installed by listing the contents of the CUDA library directory:</p>		<li><p>Check if cuDNN is installed by listing the contents of the CUDA library directory:</p>
	<~~syntaxhighlight~~ lang="bash">ls /usr/local/cuda/lib64 \| grep libcudnn</~~syntaxhighlight~~></li>		<pre lang="bash">ls /usr/local/cuda/lib64 \| grep libcudnn</pre></li>
	<li><p>If the <code>libcudnn.so.9</code> file is not present, proceed to install or update cuDNN.</p></li></ul>		<li><p>If the <code>libcudnn.so.9</code> file is not present, proceed to install or update cuDNN.</p></li></ul>
	</li>		</li>
Line 73:		Line 73:
	Installation Instructions:		Installation Instructions:

	<~~syntaxhighlight~~ lang="bash"># Download and install CUDA keyring		<pre lang="bash"># Download and install CUDA keyring
	wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb		wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
	sudo dpkg -i cuda-keyring_1.1-1_all.deb		sudo dpkg -i cuda-keyring_1.1-1_all.deb
Line 83:		Line 83:

	# For CUDA 12:		# For CUDA 12:
	sudo apt-get -y install cudnn-cuda-12</~~syntaxhighlight~~>		sudo apt-get -y install cudnn-cuda-12</pre>
	<ol start="3" style="list-style-type: decimal;">		<ol start="3" style="list-style-type: decimal;">
	<li>'''Set Environment Variables:'''		<li>'''Set Environment Variables:'''
Line 89:		Line 89:
	<li><p>Ensure that the CUDA and cuDNN libraries are included in your system’s library path.</p></li>		<li><p>Ensure that the CUDA and cuDNN libraries are included in your system’s library path.</p></li>
	<li><p>Add the following lines to your <code>~/.bashrc</code> or <code>~/.zshrc</code> file:</p>		<li><p>Add the following lines to your <code>~/.bashrc</code> or <code>~/.zshrc</code> file:</p>
	<~~syntaxhighlight~~ lang="bash">export LD_LIBRARY_PATH=/usr/local/cuda/lib64:$LD_LIBRARY_PATH		<pre lang="bash">export LD_LIBRARY_PATH=/usr/local/cuda/lib64:$LD_LIBRARY_PATH
	export PATH=/usr/local/cuda/bin:$PATH</~~syntaxhighlight~~></li>		export PATH=/usr/local/cuda/bin:$PATH</pre></li>
	<li><p>Apply the changes by sourcing the file:</p>		<li><p>Apply the changes by sourcing the file:</p>
	<~~syntaxhighlight~~ lang="bash">source ~/.bashrc</~~syntaxhighlight~~></li>		<pre lang="bash">source ~/.bashrc</pre></li>
	<li><p>This step ensures that the system can locate the CUDA and cuDNN libraries during execution.</p></li></ul>		<li><p>This step ensures that the system can locate the CUDA and cuDNN libraries during execution.</p></li></ul>
	</li>		</li>
Line 98:		Line 98:
	<ul>		<ul>
	<li><p>After installation, verify that the system recognizes the cuDNN version:</p>		<li><p>After installation, verify that the system recognizes the cuDNN version:</p>
	<~~syntaxhighlight~~ lang="bash">python -c "import torch; print(torch.backends.cudnn.version())"</~~syntaxhighlight~~></li>		<pre lang="bash">python -c "import torch; print(torch.backends.cudnn.version())"</pre></li>
	<li><p>This command should display the installed cuDNN version, confirming that PyTorch can access it.</p></li></ul>		<li><p>This command should display the installed cuDNN version, confirming that PyTorch can access it.</p></li></ul>
	</li></ol>		</li></ol>

Planetoid at 11:07, 4 December 2024

2024-12-04T11:07:22Z

← Older revision		Revision as of 19:07, 4 December 2024
Line 107:		Line 107:
	* '''Virtual Environments:''' If you’re using a virtual environment, make sure it has access to the system’s CUDA and cuDNN installations. You might need to install CUDA and cuDNN within the virtual environment or ensure that the environment variables are correctly set.		* '''Virtual Environments:''' If you’re using a virtual environment, make sure it has access to the system’s CUDA and cuDNN installations. You might need to install CUDA and cuDNN within the virtual environment or ensure that the environment variables are correctly set.

	[[Category: Generative AI]] [[Category: Software]]		[[Category: Generative AI]] [[Category: Software]] [[Category: Revised with LLMs]]

Planetoid at 11:03, 4 December 2024

2024-12-04T11:03:52Z

← Older revision		Revision as of 19:03, 4 December 2024
Line 30:		Line 30:

	<pre>whisperx input.mp3 --model large-v3 --language zh --diarize --batch_size 24 --no_align --chunk_size 10 </pre>		<pre>whisperx input.mp3 --model large-v3 --language zh --diarize --batch_size 24 --no_align --chunk_size 10 </pre>
	~~<span id="importerror-libcudnn.so.9-cannot-open-shared-object-file-no-such-file-or-directory"></span>~~
	=== ImportError: libcudnn.so.9: cannot open shared object file: No such file or directory ===		=== ImportError: libcudnn.so.9: cannot open shared object file: No such file or directory ===