Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+license: apache-2.0
+title: Fast Whisper Turbo
+sdk: gradio
+emoji: ⚡
+colorFrom: yellow
+colorTo: yellow
+short_description: Ultra-fast Whisper Turbo inference ⚡
+sdk_version: 5.0.0
+pinned: true
+preload_from_hub:
+- openai/whisper-large-v3-turbo
+---

app.py

@@ -0,0 +1,56 @@
+ABOUT = """
+# Fast Whisper Turbo ⚡
+
+Ultra-fast Whisper V3 Turbo inference, with enhancements sourced from [insanely-fast-whisper](https://github.com/Vaibhavs10/insanely-fast-whisper).
+"""
+
+CREDITS = """
+## Credits
+
+This project was made possible through the work of several other projects:
+
+- [insanely-fast-whisper](https://github.com/Vaibhavs10/insanely-fast-whisper)
+"""
+
+import subprocess
+subprocess.run(
+    "pip install flash-attn --no-build-isolation",
+    env={"FLASH_ATTENTION_SKIP_CUDA_BUILD": "TRUE"},
+    shell=True,
+) # https://huggingface.co/spaces/zero-gpu-explorers/README/discussions/75#666e4681303f0a5d67175a90
+import gradio as gr
+from transformers import pipeline
+import torch
+import spaces
+
+pipe = pipeline(
+    "automatic-speech-recognition",
+    model="openai/whisper-large-v3-turbo",
+    torch_dtype=torch.float16,
+    device="cuda:0",
+    model_kwargs={"attn_implementation": "flash_attention_2"},
+)
+
+@spaces.GPU
+def transcribe(audio, task):
+    gr.Info("Starting transcription task")
+    outputs = pipe(
+        audio,
+        chunk_length_s=30,
+        batch_size=128,
+        generate_kwargs={"task": task},
+        return_timestamps=False,
+    )
+    gr.Info("Finished transcription task")
+    return outputs['text'].strip()
+
+with gr.Blocks() as demo:
+    gr.Markdown(ABOUT)
+    audio = gr.Audio(label="Audio", type="filepath", interactive=True)
+    task = gr.Radio(["transcribe", "translate"], label="Task", value="transcribe", interactive=True)
+    btn = gr.Button("Transcribe", variant="primary")
+    output = gr.Textbox(label="Transcription", interactive=False)
+    btn.click(transcribe, inputs=[audio, task], outputs=output)
+    gr.Markdown(CREDITS)
+
+demo.queue().launch()

requirements.txt

@@ -0,0 +1 @@
+transformers[torch]