Duplicate from huggingface-projects/transformers-musicgen

Co-authored-by: Vaibhav Srivastav <reach-vb@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.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
+*.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 @@
+---
+title: Transformers Musicgen
+emoji: 📉
+colorFrom: yellow
+colorTo: pink
+sdk: gradio
+sdk_version: 3.40.1
+app_file: app.py
+pinned: false
+duplicated_from: huggingface-projects/transformers-musicgen
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,41 @@
+import gradio as gr
+import numpy as np
+import torch
+import random
+
+from transformers import AutoProcessor, MusicgenForConditionalGeneration
+
+COLORS = [
+    ["#ff0000", "#00ff00"],
+    ["#00ff00", "#0000ff"],
+    ["#0000ff", "#ff0000"],
+]
+
+path = "facebook/musicgen-large"
+processor = AutoProcessor.from_pretrained(path)
+model = MusicgenForConditionalGeneration.from_pretrained(path, torch_dtype=torch.float16).to("cuda")
+
+def predict(text):
+    
+    inputs = processor(
+        text=[text],
+        padding=True,
+        return_tensors="pt",).to("cuda")
+    
+    with torch.autocast("cuda"):
+        outputs = model.generate(**inputs, do_sample=True, guidance_scale=3, max_new_tokens=512)
+
+    return (32000, outputs[0][0].cpu().numpy().astype(np.float16)), gr.make_waveform((32000, outputs[0].cpu().numpy().astype(np.float16).ravel()), bars_color=random.choice(COLORS), bar_count=75)
+
+
+title = "MusicGen"
+
+gr.Interface(
+    fn=predict,
+    inputs=[
+        gr.Textbox(label="Text prompt"),
+    ],
+    outputs=["audio", "video"],
+    title=title,
+    theme="gradio/monochrome",
+).queue(max_size=10).launch()

requirements.txt

@@ -0,0 +1,2 @@
+transformers
+accelerate