Duplicate from ras0k/WhisperX-v2

Co-authored-by: 0 <[email protected]>

.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 +1,14 @@
+---
+title: WhisperX V2
+emoji: 🌖
+colorFrom: purple
+colorTo: indigo
+sdk: gradio
+sdk_version: 3.24.1
+app_file: app.py
+pinned: false
+license: bsd
+duplicated_from: ras0k/WhisperX-v2
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,23 @@
+import gradio as gr
+import whisperx
+import whisper
+
+def transcribe(audio_file):
+    device = "cuda" if torch.cuda.is_available() else "cpu"
+
+    # Transcribe with original Whisper
+    model = whisper.load_model("large", device)
+    result = model.transcribe(audio_file)
+
+    # Load alignment model and metadata
+    model_a, metadata = whisperx.load_align_model(language_code=result["language"], device=device)
+
+    # Align Whisper output
+    result_aligned = whisperx.align(result["segments"], model_a, metadata, audio_file, device)
+
+    return {"aligned": result_aligned["segments"], "word_segments": result_aligned["word_segments"]}
+
+inputs = gr.inputs.Audio(source="upload", type="filepath")
+outputs = gr.outputs.JSON()
+
+gr.Interface(fn=transcribe, inputs=inputs, outputs=outputs).launch()

requirements.txt

@@ -0,0 +1,2 @@
+gradio
+git+https://github.com/m-bain/whisperx.git