https://github.com/makaveli10/whisper-tflite
openai/whisper in TFLite
https://github.com/makaveli10/whisper-tflite
tflite whisper
Last synced: 2 months ago
JSON representation
openai/whisper in TFLite
- Host: GitHub
- URL: https://github.com/makaveli10/whisper-tflite
- Owner: makaveli10
- Created: 2023-06-16T07:04:19.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2023-06-16T09:40:30.000Z (almost 2 years ago)
- Last Synced: 2025-02-28T08:29:38.278Z (3 months ago)
- Topics: tflite, whisper
- Language: Python
- Homepage:
- Size: 10.7 KB
- Stars: 6
- Watchers: 1
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# whisper-tflite
## Getting Started
- Download the whisper-tiny-en tflite model from [here](https://drive.google.com/file/d/1-YRvSVbAk-hXGNXMK6wMm04eqULSPg3Q/view?usp=sharing)
- Install requirements
```bash
pip install -r requirements.txt
```
- Transcribe with tflite model
```python
from whisper_tflite import WhisperModel
model = WhisperModel("./whisper-tiny-en.tflite")
segments, _ = model.transcribe("audio.mp3")
for segment in segments:
print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
```
## References
Most of the code is taken from [faster-whisper](https://github.com/guillaumekln/faster-whisper/)