Spaces:
Runtime error
Runtime error
File size: 2,992 Bytes
41ec54b 7cb0b8e 41ec54b 9c9b591 7cb0b8e 41ec54b 9dc25d9 41ec54b d4af723 41ec54b 362c063 9c9b591 362c063 41ec54b 362c063 41ec54b d4af723 9895fa7 41ec54b 608d9e3 41ec54b 9895fa7 41ec54b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 |
import requests
import pandas as pd
import gradio as gr
from transformers import MarianMTModel, MarianTokenizer
import io
import pysrt
# Fetch and parse language options
url = "https://huggingface.co/Lenylvt/LanguageISO/resolve/main/iso.md"
response = requests.get(url)
df = pd.read_csv(io.StringIO(response.text), 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 = [(row['ISO 639-1'], f"{row['ISO 639-1']} - {row['Language Name'].strip()}") for index, row in df.iterrows()]
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
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(file_info, source_language_code, target_language_code):
# Assuming file_info is a dictionary with 'content' holding the file's bytes
file_content = file_info['content'] # Correctly access the bytes content of the file
# Use pysrt to load subtitles from the file content
subs = pysrt.open(io.BytesIO(file_content))
# Translate each subtitle
for sub in subs:
translated_text = translate_text(sub.text, source_language_code, target_language_code)
sub.text = translated_text
# Save the translated subtitles to a temporary file
output_path = "/mnt/data/translated_srt.srt"
with open(output_path, "w", encoding="utf-8") as file:
subs.save(file, encoding='utf-8')
return output_path
source_language_dropdown = gr.Dropdown(choices=language_options, label="Source Language")
target_language_dropdown = gr.Dropdown(choices=language_options, label="Target Language")
iface = gr.Interface(
fn=translate_srt,
inputs=[
gr.File(label="Upload SRT File"),
source_language_dropdown,
target_language_dropdown
],
outputs=gr.File(label="Download Translated SRT File"),
title="SRT Translator",
description="Translate SubRip Text (SRT) subtitle files. This tool uses models from the Language Technology Research Group at the University of Helsinki."
)
iface.launch()
|