Create README.md

README.md

@@ -0,0 +1,50 @@
+---
+pipeline_tag: translation
+---
+
+The model and the tokenizer are based on [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M). 
+
+We trained the model to use one sentence of context. The context is prepended to the input sentence with the `sep_token` in between. We used a subset of the [OpenSubtitles2018]( https://huggingface.co/datasets/open_subtitles) dataset for training. We trained on the interleaved dataset for all directions between the following languages: English, German, Dutch, Spanish, Italian, and Greek.
+The tokenizer of the base model was not changed. For the language codes, see the base model.
+
+Use this code for translation:
+``` from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+model_name = 'voxreality/src_ctx_aware_nllb_600M'
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
+
+max_length = 100
+src_lang = 'eng_Latn'
+tgt_lang = 'deu_Latn'
+context_text = 'This is an optional context sentence.'  # use '' empty string if not context should be used
+sentence_text = 'Text to be translated.'
+input_text = f'{context_text} {tokenizer.sep_token} {sentence_text}'
+
+tokenizer.src_lang = src_lang
+inputs = tokenizer(input_text, return_tensors='pt').to(model.device)
+model_output = model.generate(**inputs,
+                              forced_bos_token_id=tokenizer.lang_code_to_id[tgt_lang],
+                              max_length=max_length)
+output_text = tokenizer.batch_decode(model_output, skip_special_tokens=True)[0]
+
+print(output_text)
+```
+
+You can also use the pipeline
+```
+from transformers import pipeline
+
+model_name = 'voxreality/src_ctx_aware_nllb_600M'
+translation_pipeline = pipeline("translation", model=model_name)
+src_lang = 'eng_Latn'
+tgt_lang = 'deu_Latn'
+context_text = 'This is an optional context sentence.'  # use '' empty string if not context should be used
+sentence_text = 'Text to be translated.'
+input_texts = [f'{context_text} {translation_pipeline.tokenizer.sep_token} {sentence_text}']
+
+pipeline_output = translation_pipeline(input_texts, src_lang=src_lang, tgt_lang=tgt_lang)
+
+print(pipeline_output[0]['translation_text'])
+
+```