Instructions to use jacktol/whisper-large-v3-finetuned-for-ATC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jacktol/whisper-large-v3-finetuned-for-ATC with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="jacktol/whisper-large-v3-finetuned-for-ATC")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("jacktol/whisper-large-v3-finetuned-for-ATC") model = AutoModelForMultimodalLM.from_pretrained("jacktol/whisper-large-v3-finetuned-for-ATC") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,7 @@ base_model:
|
|
| 11 |
- openai/whisper-large-v3
|
| 12 |
pipeline_tag: automatic-speech-recognition
|
| 13 |
model-index:
|
| 14 |
-
- name: Whisper Large
|
| 15 |
results:
|
| 16 |
- task:
|
| 17 |
type: automatic-speech-recognition
|
|
@@ -25,13 +25,13 @@ model-index:
|
|
| 25 |
|
| 26 |
---
|
| 27 |
|
| 28 |
-
# Whisper Large
|
| 29 |
|
| 30 |
## Model Overview
|
| 31 |
|
| 32 |
This model is a fine-tuned version of OpenAI's Whisper Large v3 model, specifically trained on **Air Traffic Control (ATC)** communication datasets. The fine-tuning process significantly improves transcription accuracy on domain-specific aviation communications, achieving a Word Error Rate (WER) of 6.5% on the test set. The model is particularly effective at handling accent variations and ambiguous phrasing often encountered in ATC communications.
|
| 33 |
|
| 34 |
-
- **Base Model**: OpenAI Large
|
| 35 |
- **Fine-tuned Model WER**: 6.5%
|
| 36 |
|
| 37 |
## Model Description
|
|
|
|
| 11 |
- openai/whisper-large-v3
|
| 12 |
pipeline_tag: automatic-speech-recognition
|
| 13 |
model-index:
|
| 14 |
+
- name: Whisper Large v3 Fine-Tuned for Air Traffic Control (ATC)
|
| 15 |
results:
|
| 16 |
- task:
|
| 17 |
type: automatic-speech-recognition
|
|
|
|
| 25 |
|
| 26 |
---
|
| 27 |
|
| 28 |
+
# Whisper Large v3 Fine-Tuned for Air Traffic Control (ATC)
|
| 29 |
|
| 30 |
## Model Overview
|
| 31 |
|
| 32 |
This model is a fine-tuned version of OpenAI's Whisper Large v3 model, specifically trained on **Air Traffic Control (ATC)** communication datasets. The fine-tuning process significantly improves transcription accuracy on domain-specific aviation communications, achieving a Word Error Rate (WER) of 6.5% on the test set. The model is particularly effective at handling accent variations and ambiguous phrasing often encountered in ATC communications.
|
| 33 |
|
| 34 |
+
- **Base Model**: OpenAI Large v3
|
| 35 |
- **Fine-tuned Model WER**: 6.5%
|
| 36 |
|
| 37 |
## Model Description
|