Update app.py

app.py

@@ -1,12 +1,3 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-
-# This source code is licensed under the license found in the
-# LICENSE file in the root directory of this source tree.
-
-# Updated to account for UI changes from https://github.com/rkfg/audiocraft/blob/long/app.py
-# also released under the MIT license.
-
 import argparse
 from concurrent.futures import ProcessPoolExecutor
 import os
@@ -19,6 +10,7 @@ import warnings
 
 import torch
 import gradio as gr
+import pydub
 
 from audiocraft.data.audio_utils import convert_audio
 from audiocraft.data.audio import audio_write
@@ -123,11 +115,11 @@ def _do_predictions(texts, melodies, duration, progress=False, **gen_kwargs):
     outputs = outputs.detach().cpu().float()
     out_files = []
     for output in outputs:
-        with NamedTemporaryFile("wb", suffix=".wav", delete=False) as file:
+        with NamedTemporaryFile("wb", suffix=".mp3", delete=False) as file:
             audio_write(
                 file.name, output, MODEL.sample_rate, strategy="loudness",
                 loudness_headroom_db=16, loudness_compressor=True, add_suffix=False)
-            out_files.append(pool.submit(make_waveform, file.name))
+            out_files.append(file.name)
             file_cleaner.add(file.name)
     res = [out_file.result() for out_file in out_files]
     for file in res:
@@ -211,7 +203,7 @@ def ui_full(launch_kwargs):
                     temperature = gr.Number(label="Temperature", value=1.0, interactive=True)
                     cfg_coef = gr.Number(label="Classifier Free Guidance", value=3.0, interactive=True)
             with gr.Column():
-                output = gr.Video(label="Generated Music")
+                output = gr.Audio(label="Generated Music")
         submit.click(predict_full,
                      inputs=[model, text, melody, duration, topk, topp, temperature, cfg_coef],
                      outputs=[output])
@@ -305,7 +297,7 @@ def ui_batched(launch_kwargs):
                 with gr.Row():
                     submit = gr.Button("Generate")
             with gr.Column():
-                output = gr.Video(label="Generated Music")
+                output = gr.Audio(label="Generated Music")
         submit.click(predict_batched, inputs=[text, melody],
                      outputs=[output], batch=True, max_batch_size=MAX_BATCH_SIZE)
         radio.change(toggle_audio_src, radio, [melody], queue=False, show_progress=False)