Automatic Speech Recognition
Transformers
Safetensors
PyTorch
arkasr
text-generation
speech
audio
multilingual
hotword
audio8
custom_code
Eval Results
Instructions to use Audio8/Audio8-ASR-0.1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Audio8/Audio8-ASR-0.1B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Audio8/Audio8-ASR-0.1B", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Audio8/Audio8-ASR-0.1B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Embed demo video in model card
Browse files
README.md
CHANGED
|
@@ -52,6 +52,18 @@ configuration, and workload.
|
|
| 52 |
The iOS release is designed for local iPhone transcription with roughly 200 MB
|
| 53 |
peak runtime memory footprint, depending on device, iOS version, and workload.
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
## Evaluation Results
|
| 56 |
|
| 57 |
| Evaluation suite | Dataset / split | Language | Metric | Score (%) | H200 RTFx |
|
|
|
|
| 52 |
The iOS release is designed for local iPhone transcription with roughly 200 MB
|
| 53 |
peak runtime memory footprint, depending on device, iOS version, and workload.
|
| 54 |
|
| 55 |
+
## Demo Video
|
| 56 |
+
|
| 57 |
+
<p align="center">
|
| 58 |
+
<video src="assets/audio8-teaser-aurora-redesign-final.mp4" controls preload="metadata" width="720">
|
| 59 |
+
Your browser does not support the video tag.
|
| 60 |
+
</video>
|
| 61 |
+
</p>
|
| 62 |
+
|
| 63 |
+
<p align="center">
|
| 64 |
+
<a href="assets/audio8-teaser-aurora-redesign-final.mp4">Open the demo video</a>
|
| 65 |
+
</p>
|
| 66 |
+
|
| 67 |
## Evaluation Results
|
| 68 |
|
| 69 |
| Evaluation suite | Dataset / split | Language | Metric | Score (%) | H200 RTFx |
|