initial commit

app.py

@@ -0,0 +1,127 @@
+import gradio as gr
+from PIL import Image  
+import re
+import os
+import speech_recognition as sr
+
+
+stable_diffusion = gr.Blocks.load(name="spaces/stabilityai/stable-diffusion")
+r = sr.Recognizer()
+
+def transcribe(audio):
+    with sr.AudioFile(audio) as source:
+        audio_ = r.listen(source) 
+        text = r.recognize_google(audio_)#, language = 'en-IN')# , show_all=True)
+    return text
+
+#########
+
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
+# import torch
+
+# this model was loaded from https://hf.co/models
+model = AutoModelForSeq2SeqLM.from_pretrained("facebook/nllb-200-distilled-600M")
+tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-200-distilled-600M")
+device = -1 #0 if torch.cuda.is_available() else -1
+LANGS = ["ace_Arab", "eng_Latn", "fra_Latn", "spa_Latn"]
+
+def translate(text, src_lang, tgt_lang):
+    """
+    Translate the text from source lang to target lang
+    """
+    translation_pipeline = pipeline("translation", model=model, tokenizer=tokenizer, src_lang=src_lang, tgt_lang=tgt_lang, max_length=400, device=device)
+    result = translation_pipeline(text)
+    return result[0]['translation_text']
+
+# demo = gr.Interface(
+#     fn=translate,
+#     inputs=[
+#         gr.components.Textbox(label="Text"),
+#         gr.components.Dropdown(label="Source Language", choices=LANGS),
+#         gr.components.Dropdown(label="Target Language", choices=LANGS),
+#     ],
+#     outputs=["text"],
+#     examples=[["Building a translation demo with Gradio is so easy!", "eng_Latn", "spa_Latn"]],
+#     cache_examples=False,
+#     title="Translation Demo",
+#     description="This demo is a simplified version of the original [NLLB-Translator](https://huggingface.co/spaces/Narrativaai/NLLB-Translator) space"
+# )
+
+
+with gr.Blocks() as demo:
+
+    gr.Markdown("Translate your voice to any of following language - Speech to text -> Translation - Facebook NLL")
+    with gr.Tab("Audio Input"):
+        audio_input = gr.Audio(source="microphone", type="filepath")
+        sr_lang1 = gr.Dropdown(label="Source Language", choices=LANGS)
+        tr_lang1 = gr.Dropdown(label="Target Language", choices=LANGS)
+        submit_audio_button = gr.Button("Translate")
+        text_output = gr.Textbox(label="You said:")
+        
+    with gr.Tab("Text Input"):
+        text_input = gr.Textbox(label="Enter text")
+        sr_lang = gr.Dropdown(label="Source Language", choices=LANGS)
+        tr_lang = gr.Dropdown(label="Target Language", choices=LANGS)
+        submit_button_text = gr.Button("Translate")
+
+
+    
+    translated_output = gr.Textbox(label="Output Box")
+    # sd_output = gr.Gallery().style(grid=2, height="auto")
+
+    submit_audio_button.click(fn=transcribe, inputs=audio_input, outputs=text_output)
+    text_output.change(fn=translate, inputs=[text_output, sr_lang1, tr_lang1], outputs=translated_output)
+    submit_button_text.click(fn=translate, inputs=[text_input, sr_lang2, tr_lang2], outputs=translated_output)
+
+
+demo.launch()
+
+
+##########
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+# def get_images(prompt):
+#     gallery_dir = stable_diffusion(prompt, fn_index=2)
+#     return [os.path.join(gallery_dir, img) for img in os.listdir(gallery_dir)]
+
+# with gr.Blocks() as demo:
+
+#     gr.Markdown("Stable diffusion magic -> Get the photo from whatever you can think of!")
+#     with gr.Tab("Audio Input"):
+#         audio_input = gr.Audio(source="microphone", type="filepath")
+#         submit_audio_button = gr.Button("Convert to Image")
+#         text_output = gr.Textbox(label="Recorded text")
+        
+#     with gr.Tab("Text Input"):
+#         text_input = gr.Textbox(label="Enter text")
+#         submit_button_text = gr.Button("Convert to Image")
+
+
+    
+#     # output = gr.Textbox(label="Output Box")
+#     sd_output = gr.Gallery().style(grid=2, height="auto")
+
+#     submit_audio_button.click(fn=transcribe, inputs=audio_input, outputs=text_output)
+#     text_output.change(fn=get_images, inputs=text_output, outputs=sd_output)
+#     submit_button_text.click(fn=get_images, inputs=text_input, outputs=sd_output)
+
+
+# demo.launch()
+
+
+
+
+

requirements.txt

@@ -0,0 +1,2 @@
+SpeechRecognition==3.8.1
+transformers