Person screaming

app.py

@@ -34,7 +34,6 @@ def text2audio(text, negative_prompt, duration, guidance_scale, random_seed, n_c
         text,
         audio_length_in_s=duration,
         guidance_scale=guidance_scale,
-        num_inference_steps=100,
         negative_prompt=negative_prompt,
         num_waveforms_per_prompt=n_candidates if n_candidates else 1,
         generator=generator.manual_seed(int(random_seed)),
@@ -195,8 +194,8 @@ with iface:
                 duration = gr.Slider(2.5, 10, value=5, step=2.5, label="Duration (seconds)")
                 guidance_scale = gr.Slider(
                     0,
-                    5,
-                    value=3.5,
+                    4,
+                    value=2.5,
                     step=0.5,
                     label="Guidance scale",
                     info="Large => better quality and relevancy to text; Small => better diversity",

requirements.txt

@@ -1,4 +1,4 @@
 git+https://github.com/huggingface/diffusers.git
 git+https://github.com/huggingface/transformers.git
 --extra-index-url https://download.pytorch.org/whl/cu113
-torch<2.1.0
+torch >= 2.0