TheStageAI/thewhisper-large-v3-turbo
Automatic Speech Recognition
•
0.8B
•
Updated
•
2.19k
•
14
AI & ML interests
None defined yet.
Recent Activity
View all activity
quazim
updated
a
model
3 days ago
Update README.md
#2 opened 6 days ago
by
hypothetical
hypothetical
posted
an
update
7 days ago
Post
2565
We thought it would be easier, but finally we have integrated CuDNN Paged Attention to our models!
Read article here: https://app.thestage.ai/blog/Integrating-cuDNN-Paged-Attention-to-TheStage-AI-Inference?id=8
Llama-8B with CuDNN paged attention, including B200 support: TheStageAI/Elastic-Llama-3.1-8B-Instruct
Mistral-Small-24B with CuDNN paged attention, including B200 support: TheStageAI/Elastic-Mistral-Small-3.1-24B-Instruct-2503
Read article here: https://app.thestage.ai/blog/Integrating-cuDNN-Paged-Attention-to-TheStage-AI-Inference?id=8
Llama-8B with CuDNN paged attention, including B200 support: TheStageAI/Elastic-Llama-3.1-8B-Instruct
Mistral-Small-24B with CuDNN paged attention, including B200 support: TheStageAI/Elastic-Mistral-Small-3.1-24B-Instruct-2503
psynote123
published
a
model
7 days ago
psynote123
updated
a
model
7 days ago
hypothetical
published
a
model
7 days ago
hinairo
updated
2
models
8 days ago
add languages, base model, update license
#3 opened 14 days ago
by
hypothetical
hypothetical
posted
an
update
14 days ago
Post
2014
We have updated our transcription model:
TheStageAI/thewhisper-large-v3-turbo
– 6.00 WER on the English Open ASR Leaderboard
– 4.74 WER on the Multilingual Open ASR Leaderboard
– Beats NVIDIA Parakeet (6.34 WER) and Whisper-large-v3-turbo (7.8 WER)
– Strong improvements in Arabic, Hindi, Chinese
– Maintains quality with background and environmental noise
– Optimized inference engines for NVIDIA and Apple
– Hugging Face Transformers interface for easy use
– Best-in-class speed on NVIDIA GPUs and power efficiency on Apple devices
– NVIDIA Jetson Thor support
– 6.00 WER on the English Open ASR Leaderboard
– 4.74 WER on the Multilingual Open ASR Leaderboard
– Beats NVIDIA Parakeet (6.34 WER) and Whisper-large-v3-turbo (7.8 WER)
– Strong improvements in Arabic, Hindi, Chinese
– Maintains quality with background and environmental noise
– Optimized inference engines for NVIDIA and Apple
– Hugging Face Transformers interface for easy use
– Best-in-class speed on NVIDIA GPUs and power efficiency on Apple devices
– NVIDIA Jetson Thor support
-
- 2 replies
update-checkpoint-v2
#2 opened 14 days ago
by
quazim
hypothetical
updated
a
collection
15 days ago
hypothetical
posted
an
update
about 2 months ago
Post
266
Hello guys! Maybe someone want to test our framework for automated model's compression. Here is what can be produced with it. Move the slider - compress/accelerate model, select point which like and compile. I can give an access, we are now improving and collecting comments from users
TheStageAI/ANNA-LLM
TheStageAI/ANNA-LLM
- 3 replies
quazim
updated
a
Space
about 2 months ago
quazim
published
a
Space
about 2 months ago
quazim
updated
a
Space
about 2 months ago