https://github.com/cahya-wirawan/indonesian-whisperer
Experiment with OpenAI Whisper on Indonesian Languages
Science Score: 26.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
✓.zenodo.json file
Found .zenodo.json file -
○DOI references
-
○Academic publication links
-
○Committers with academic emails
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (3.1%) to scientific vocabulary
Repository
Experiment with OpenAI Whisper on Indonesian Languages
Basic Info
- Host: GitHub
- Owner: cahya-wirawan
- License: mit
- Language: Python
- Default Branch: main
- Size: 65.4 KB
Statistics
- Stars: 10
- Watchers: 3
- Forks: 3
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
Indonesian Whisperer
Experiment with OpenAI Whisper on Indonesian Languages.
OpenAI Whisper
Development
Try the Demo of our Speech Recognition models. The inference is running on NVidia T4, which is provided generously by Huggingface for free.
Dependencies Installation
Fine Tuning
We fine-tuned the original OpenAI Whisper with several Indonesian datasets.
| Model | WER on CV11 | |-----------------------------------------------------------------------------|-------------| | Indonesian Whisper Tiny | 18.28 | | Indonesian Whisper Small | 6.06 | | Indonesian Whisper Medium | 3.83 | | Indonesian Whisper Large | 6.25* |
The original OpenAI Whisper Medium model has WER of 12.x, but we got 3.83 after fine-tuning it with Indonesian datasets.
*The WER of Indonesian Whisper Large is worst than the Medium and Small model because we fine-tuned it with fewer epochs than the other models.
Inference Pipeline
Authors
Following are the authors of this work (listed alphabetically):
Owner
- Name: Cahya Wirawan
- Login: cahya-wirawan
- Kind: user
- Location: Vienna, Austria
- Website: https://www.linkedin.com/in/cahyawirawan/
- Twitter: CahyaWr
- Repositories: 171
- Profile: https://github.com/cahya-wirawan
System engineer, currently working on NLP, CV and Speech Recognition for fun and curiosity
GitHub Events
Total
- Watch event: 4
Last Year
- Watch event: 4
Committers
Last synced: about 1 year ago
Top Committers
| Name | Commits | |
|---|---|---|
| Cahya Wirawan | c****n@g****m | 21 |
Issues and Pull Requests
Last synced: about 1 year ago
All Time
- Total issues: 0
- Total pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Total issue authors: 0
- Total pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0
Past Year
- Issues: 0
- Pull requests: 0
- Average time to close issues: N/A
- Average time to close pull requests: N/A
- Issue authors: 0
- Pull request authors: 0
- Average comments per issue: 0
- Average comments per pull request: 0
- Merged pull requests: 0
- Bot issues: 0
- Bot pull requests: 0