Update app.py

app.py

@@ -11,6 +11,7 @@ from PIL import Image
 import spaces
 import torch
 from diffusers import DiffusionPipeline
+from huggingface_hub import Client
 
 DESCRIPTION = """# Playground v2.5"""
 if not torch.cuda.is_available():
@@ -26,7 +27,14 @@ device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 
 NUM_IMAGES_PER_PROMPT = 1
 
-valid_languages = {'fon', 'fr', 'yo', 'en'}
+languages = {
+    "fon": "fon (Fon)",
+    "yo": "yo (Yoruba)",
+    "fr": "fra (French)",
+    "en": "eng (English)"
+}
+
+valid_languages = set(languages.keys())
 
 if torch.cuda.is_available():
     pipe = DiffusionPipeline.from_pretrained(
@@ -79,7 +87,7 @@ def translate_to_english(phrase, src_lang):
 
 @spaces.GPU(enable_queue=True)
 def generate(
-    phrase: str,
+    audio,
     input_lang: str,
     negative_prompt: str = "",
     use_negative_prompt: bool = False,
@@ -95,13 +103,23 @@ def generate(
     seed = int(randomize_seed_fn(seed, randomize_seed))
     generator = torch.Generator().manual_seed(seed)
 
+    client = Client("https://afrinetwork-speak.hf.space/")
+    language_name = languages[input_lang]
+    result = client.predict(
+        "Record from Mic",
+        audio,
+        language_name,
+        api_name="/predict"
+    )
+    transcript = result["transcription"]
+
     if input_lang != 'en':
-        prompt = translate_to_english(phrase, input_lang)
+        prompt = translate_to_english(transcript, input_lang)
     else:
-        prompt = phrase
+        prompt = transcript
 
     if not use_negative_prompt:
-        negative_prompt = None
+        negative_prompt = None  # type: ignore
 
     images = pipe(
         prompt=prompt,
@@ -122,12 +140,12 @@ def generate(
 
 
 examples = [
-    ["neon holography crystal cat", "en"],
-    ["a cat eating a piece of cheese", "en"],
-    ["an astronaut riding a horse in space", "en"],
-    ["a cartoon of a boy playing with a tiger", "en"],
-    ["a cute robot artist painting on an easel, concept art", "en"],
-    ["a close up of a woman wearing a transparent, prismatic, elaborate nemeses headdress, over the shoulder pose, brown skin-tone", "en"]
+    "neon holography crystal cat",
+    "a cat eating a piece of cheese",
+    "an astronaut riding a horse in space",
+    "a cartoon of a boy playing with a tiger",
+    "a cute robot artist painting on an easel, concept art",
+    "a close up of a woman wearing a transparent, prismatic, elaborate nemeses headdress, over the should pose, brown skin-tone"
 ]
 
 css = '''
@@ -143,14 +161,8 @@ with gr.Blocks(css=css) as demo:
     )
     with gr.Group():
         with gr.Row():
-            input_lang = gr.Dropdown(choices=list(valid_languages), value='en', label='Input Language')
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
+            input_lang = gr.Dropdown(choices=list(languages.values()), value='eng (English)', label='Input Language')
+            audio = gr.Audio(source="microphone", type="filepath", label="Audio Input")
             run_button = gr.Button("Run", scale=0)
         result = gr.Gallery(label="Result", columns=NUM_IMAGES_PER_PROMPT, show_label=False)
     with gr.Accordion("Advanced options", open=False):
@@ -160,7 +172,7 @@ with gr.Blocks(css=css) as demo:
                 label="Negative prompt",
                 max_lines=1,
                 placeholder="Enter a negative prompt",
-                visible=False,
+                visible=True,
             )
         seed = gr.Slider(
             label="Seed",
@@ -196,40 +208,39 @@ with gr.Blocks(css=css) as demo:
 
     gr.Examples(
         examples=examples,
-        inputs=[prompt, input_lang],
+        inputs=[audio, input_lang],
         outputs=[result, seed],
         fn=generate,
         cache_examples=CACHE_EXAMPLES,
     )
-
     use_negative_prompt.change(
-        fn=lambda x: gr.update(visible=x),
-        inputs=use_negative_prompt,
-        outputs=negative_prompt,
-        api_name=False,
-    )
-
-    gr.on(
-        triggers=[
-            prompt.submit,
-            negative_prompt.submit,
-            run_button.click,
-        ],
-        fn=generate,
-        inputs=[
-            prompt,
-            input_lang,
-            negative_prompt,
-            use_negative_prompt,
-            seed,
-            width,
-            height,
-            guidance_scale,
-            randomize_seed,
-        ],
-        outputs=[result, seed],
-        api_name="run",
-    )
+       fn=lambda x: gr.update(visible=x),
+       inputs=use_negative_prompt,
+       outputs=negative_prompt,
+       api_name=False,
+   )
+
+   gr.on(
+       triggers=[
+           audio.upload,
+           negative_prompt.submit,
+           run_button.click,
+       ],
+       fn=generate,
+       inputs=[
+           audio,
+           input_lang,
+           negative_prompt,
+           use_negative_prompt,
+           seed,
+           width,
+           height,
+           guidance_scale,
+           randomize_seed,
+       ],
+       outputs=[result, seed],
+       api_name="run",
+   )
 
 if __name__ == "__main__":
-    demo.queue(max_size=20).launch()
+   demo.queue(max_size=20).launch()