Automatic Speech Recognition
Transformers
Safetensors
PyTorch
arkasr
text-generation
speech
audio
ark-asr
custom_code
Eval Results
Instructions to use Audio8/ARK-ASR-0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Audio8/ARK-ASR-0.6B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Audio8/ARK-ASR-0.6B", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("Audio8/ARK-ASR-0.6B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
AutoArk-AI commited on
Commit ·
45776b5
1
Parent(s): e55e9b8
Add TEDLIUM WER eval result
Browse files
.eval_results/open_asr_leaderboard.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
- dataset:
|
| 2 |
id: hf-audio/open-asr-leaderboard
|
| 3 |
task_id: mean_wer
|
| 4 |
-
value: 5.
|
| 5 |
date: '2026-06-17'
|
| 6 |
source:
|
| 7 |
url: https://huggingface.co/hf-audio
|
|
@@ -78,6 +78,16 @@
|
|
| 78 |
name: open-asr-leaderboard
|
| 79 |
user: hf-audio
|
| 80 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
- dataset:
|
| 82 |
id: hf-audio/open-asr-leaderboard
|
| 83 |
task_id: voxpopuli_wer
|
|
|
|
| 1 |
- dataset:
|
| 2 |
id: hf-audio/open-asr-leaderboard
|
| 3 |
task_id: mean_wer
|
| 4 |
+
value: 5.53
|
| 5 |
date: '2026-06-17'
|
| 6 |
source:
|
| 7 |
url: https://huggingface.co/hf-audio
|
|
|
|
| 78 |
name: open-asr-leaderboard
|
| 79 |
user: hf-audio
|
| 80 |
|
| 81 |
+
- dataset:
|
| 82 |
+
id: hf-audio/open-asr-leaderboard
|
| 83 |
+
task_id: tedlium_wer
|
| 84 |
+
value: 2.45
|
| 85 |
+
date: '2026-06-17'
|
| 86 |
+
source:
|
| 87 |
+
url: https://huggingface.co/hf-audio
|
| 88 |
+
name: open-asr-leaderboard
|
| 89 |
+
user: hf-audio
|
| 90 |
+
|
| 91 |
- dataset:
|
| 92 |
id: hf-audio/open-asr-leaderboard
|
| 93 |
task_id: voxpopuli_wer
|