Create app.py

app.py

@@ -0,0 +1,66 @@
+import streamlit as st
+import pandas as pd
+import pysrt
+from transformers import MarianMTModel, MarianTokenizer
+
+# Fetch and parse language options from the provided URL
+url = "https://huggingface.co/Lenylvt/LanguageISO/resolve/main/iso.md"
+df = pd.read_csv(url, delimiter="|", skiprows=2, header=None).dropna(axis=1, how='all')
+df.columns = ['ISO 639-1', 'ISO 639-2', 'Language Name', 'Native Name']
+df['ISO 639-1'] = df['ISO 639-1'].str.strip()
+
+# Prepare language options for the dropdown
+language_options = df.set_index('ISO 639-1')[['Language Name']].to_dict()['Language Name']
+
+def translate_text(text, source_language_code, target_language_code):
+    # Construct model name using ISO 639-1 codes
+    model_name = f"Helsinki-NLP/opus-mt-{source_language_code}-{target_language_code}"
+
+    # Check if source and target languages are the same, which is not supported for translation
+    if source_language_code == target_language_code:
+        return "Translation between the same languages is not supported."
+
+    # Load tokenizer and model
+    try:
+        tokenizer = MarianTokenizer.from_pretrained(model_name)
+        model = MarianMTModel.from_pretrained(model_name)
+    except Exception as e:
+        return f"Failed to load model for {source_language_code} to {target_language_code}: {str(e)}"
+
+    # Translate text
+    translated = model.generate(**tokenizer(text, return_tensors="pt", padding=True, truncation=True, max_length=512))
+    translated_text = tokenizer.decode(translated[0], skip_special_tokens=True)
+    
+    return translated_text
+
+def translate_srt(input_file, source_language_code, target_language_code):
+    # Load SRT file
+    subs = pysrt.open(input_file.name)
+
+    # Initialize an empty list to store translated subtitles
+    translated_subs = []
+
+    # Translate each subtitle
+    for idx, sub in enumerate(subs):
+        translated_text = translate_text(sub.text, source_language_code, target_language_code)
+        # Construct the translated subtitle with timestamp and line number
+        translated_sub = pysrt.SubRipItem(index=idx+1, start=sub.start, end=sub.end, text=translated_text)
+        translated_subs.append(translated_sub)
+
+    # Save translated subtitles to a new SRT file
+    translated_file = pysrt.SubRipFile(translated_subs)
+    translated_srt_path = input_file.name.replace(".srt", f"_{target_language_code}.srt")
+    translated_file.save(translated_srt_path)
+    return translated_srt_path
+
+st.title("SRT Translator")
+st.write("Translate subtitles from one language to another.")
+
+source_language_code = st.selectbox("Select Source Language", options=list(language_options.keys()))
+target_language_code = st.selectbox("Select Target Language", options=list(language_options.keys()))
+
+file_input = st.file_uploader("Upload SRT File", type=["srt"])
+
+if file_input is not None:
+    translated_srt_path = translate_srt(file_input, source_language_code, target_language_code)
+    st.success(f"Translation complete! You can download the translated SRT file from [here]({translated_srt_path})")