Upload folder using huggingface_hub

.gitattributes

@@ -59,3 +59,4 @@ songs/Heal[[:space:]]the[[:space:]]World/vocals.wav filter=lfs diff=lfs merge=lf
 songs/Man[[:space:]]in[[:space:]]the[[:space:]]mirror/instrumentals.wav filter=lfs diff=lfs merge=lfs -text
 songs/Man[[:space:]]in[[:space:]]the[[:space:]]mirror/vocals.wav filter=lfs diff=lfs merge=lfs -text
 songs/cover.png filter=lfs diff=lfs merge=lfs -text
+inference_output/vocals.wav filter=lfs diff=lfs merge=lfs -text

code_v2.py

@@ -23,6 +23,9 @@ load_dotenv()
 
 OpenAI.api_key = os.getenv('OPENAI_API_KEY')
 
+logo_image_path = "Logo.png"  
+alchemy_image_path = "Alchemy AI.png"  
+technation_logo_blk = "technation_logo_blk.png"
 
 
 client = OpenAI(
@@ -35,7 +38,8 @@ SONGS_DIR = CURRENT_DIR / "songs"
 INFERENCE_OUTPUT_DIRNAME = CURRENT_DIR / "inference_output"
 COVER_IMAGE_PATH = SONGS_DIR / "cover.png"
 
-logo_image_path = CURRENT_DIR / "Logo.png" 
+logo_image_path = CURRENT_DIR / "Logo.png"  
+
 
 # Ensure the inference output directory exists
 INFERENCE_OUTPUT_DIRNAME.mkdir(parents=True, exist_ok=True)
@@ -237,7 +241,7 @@ css = """
 # Gradio app with custom CSS and theme
 with gr.Blocks(css=css) as app:
     with gr.Row():
-            gr.Image(logo_image_path, container=True, show_label=False, show_download_button=False)
+            gr.Image(logo_image_path, container=False, show_label=False, show_download_button=False)
 
 
 
@@ -263,8 +267,8 @@ with gr.Blocks(css=css) as app:
             converted_mix_audio = gr.Audio(label="Converted Mix (Converted Vocals + Instrumentals)", type="filepath")
             convert_button.click(voice_conversion, inputs=[person_dropdown, song_dropdown], outputs=[converted_mix_audio])
 
-            generate_button = gr.Button("Generate Caption and Image")
+            generate_button = gr.Button("Generate Social Media Post")
             generate_button.click(gen_caption_image, inputs=[song_dropdown, person_dropdown], outputs=[gr.Image(label="Generated Image", type="numpy", height=300), gr.Textbox(label="Generated Caption")])
 
 if __name__ == "__main__":
-    app.launch()
+    app.launch(share = True)

inference_output/Billie Jean_converted_mix.wav

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dab4a392ad7028f4c73362884ab22465ced9259698a126d94e3ea1c47c9a3e2
+oid sha256:ad51b2faadf9ffa9252d6ddbece26ceb37f50c5b27cd61a16968407d8ec51751
 size 1764044

people/Bruno Mars/G_124930.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78db44697f188da3b1bb6d28ff5579da0df77ddab2121bb989cf685b76dd942b
+size 542789469

people/Bruno Mars/config.json

@@ -0,0 +1,98 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 4805,
+    "seed": 1234,
+    "epochs": 4040,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 8,
+    "fp16_run": false,
+    "bf16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 10240,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "use_sr": true,
+    "max_speclen": 512,
+    "port": "8001",
+    "keep_ckpts": 3,
+    "num_workers": 4,
+    "log_version": 0,
+    "ckpt_name_by_step": true,
+    "accumulate_grad_batches": 1
+  },
+  "data": {
+    "training_files": "filelists/44k/train.txt",
+    "validation_files": "filelists/44k/val.txt",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": 22050
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0.1,
+    "resblock": "1",
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
+    "resblock_dilation_sizes": [
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "upsample_rates": [
+      8,
+      8,
+      2,
+      2,
+      2
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "ssl_dim": 256,
+    "n_speakers": 200
+  },
+  "spk": {
+    "BrunoMars": 0
+  }
+}

people/Bruno Mars/description.txt

@@ -0,0 +1 @@
+A dynamic performer recognized for his catchy pop and R&B hits, and energetic live performances.

requirements.txt

@@ -1,4 +1,9 @@
 so-vits-svc-fork
 gradio
 openai
-python-dotenv
+python-dotenv
+numpy 
+librosa 
+scipy  
+Pillow 
+requests