Spaces:

sanchit-gandhi
/

whisper-jax-spaces

Running on TPU v5e

sanchit-gandhi HF staff commited on Apr 24

Commit

20dea74

•

1 Parent(s): f72311b

tpu v5e

Files changed (1) hide show

app.py CHANGED Viewed

@@ -26,14 +26,14 @@ YT_LENGTH_LIMIT_S = 7200  # limit to 2 hour YouTube files
 title = "Whisper JAX: The Fastest Whisper API ⚡️"
-description = """Whisper JAX is an optimised implementation of the [Whisper model](https://huggingface.co/openai/whisper-large-v3) by OpenAI. It runs on JAX with a TPU v4-8 in the backend. Compared to PyTorch on an A100 GPU, it is over [**70x faster**](https://github.com/sanchit-gandhi/whisper-jax#benchmarks), making it the fastest Whisper API available.
 Note that at peak times, you may find yourself in the queue for this demo. When you submit a request, your queue position will be shown in the top right-hand side of the demo pane. Once you reach the front of the queue, your audio file will be transcribed, with the progress displayed through a progress bar.
-To skip the queue, you may wish to create your own inference endpoint, details for which can be found in the [Whisper JAX repository](https://github.com/sanchit-gandhi/whisper-jax#creating-an-endpoint).
 """
-article = "Whisper large-v3 model by OpenAI. Backend running JAX on a TPU v4-8 through the generous support of the [TRC](https://sites.research.google/trc/about/) programme. Whisper JAX [code](https://github.com/sanchit-gandhi/whisper-jax) and Gradio demo by 🤗 Hugging Face."
 language_names = sorted(TO_LANGUAGE_CODE.keys())

 title = "Whisper JAX: The Fastest Whisper API ⚡️"
+description = """Whisper JAX is an optimised implementation of the [Whisper model](https://huggingface.co/openai/whisper-large-v3) by OpenAI. This demo is running on JAX with a TPU v5e backend. Compared to PyTorch on an A100 GPU, it is over [**70x faster**](https://github.com/sanchit-gandhi/whisper-jax#benchmarks), making it the fastest Whisper API available.
 Note that at peak times, you may find yourself in the queue for this demo. When you submit a request, your queue position will be shown in the top right-hand side of the demo pane. Once you reach the front of the queue, your audio file will be transcribed, with the progress displayed through a progress bar.
+To skip the queue, you may wish to create your own inference endpoint by duplicating the demo, details for which can be found in the [Whisper JAX repository](https://github.com/sanchit-gandhi/whisper-jax#creating-an-endpoint).
 """
+article = "Whisper large-v3 model by OpenAI. Backend running JAX on a TPU v5e directly through Hugging Face Spaces. Whisper JAX [code](https://github.com/sanchit-gandhi/whisper-jax) and Gradio demo by 🤗 Hugging Face."
 language_names = sorted(TO_LANGUAGE_CODE.keys())