Update README.md

Update data section

README.md

@@ -29,8 +29,8 @@ library_name: transformers
 
 # Transnormer 19th century (beta v02)
 
-This model normalizes spelling variants in historical German text to the modern spelling.
-We fine-tuned [google/byt5-small](https://huggingface.co/google/byt5-small) on a modified version of the [DTA EvalCorpus](https://kaskade.dwds.de/~moocow/software/dtaec/) (1780-1901).
+This model generates a normalized version of historical input text for German from the 19th (and late 18th) century.  
+The base model [google/byt5-small](https://huggingface.co/google/byt5-small) was fine-tuned on a modified version of the [DTA EvalCorpus](https://kaskade.dwds.de/~moocow/software/dtaec/) (see section [Training and evaluation data](#training-and-evaluation-data)).
 
 ## Model description
 
@@ -43,7 +43,7 @@ tokenizer = AutoTokenizer.from_pretrained("ybracke/transnormer-19c-beta-v02")
 model = AutoModelForSeq2SeqLM.from_pretrained("ybracke/transnormer-19c-beta-v02")
 sentence = "Die Königinn ſaß auf des Pallaſtes mittlerer Tribune."
 inputs = tokenizer(sentence, return_tensors="pt",)
-outputs = model.generate(**inputs, max_length=128)
+outputs = model.generate(**inputs, num_beams=4, max_length=128)
 print(tokenizer.batch_decode(outputs, skip_special_tokens=True))
 # >>> ['Die Königin saß auf des Palastes mittlerer Tribüne.']
 ```
@@ -58,13 +58,13 @@ print(transnormer(sentence))
 # >>> [{'generated_text': 'Die Königin saß auf des Palastes mittlerer Tribüne.'}]
 ```
 
-## Intended uses & limitations
+## Training and evaluation data
 
-More information needed
+The model was fine-tuned and evaluated on splits derived from the [DTA EvalCorpus](https://kaskade.dwds.de/~moocow/software/dtaec/), a parallel corpus containing of 121 texts from Deutsches Textarchiv (German Text Archive). The corpus was originally created by aligning historic prints in original spelling with an edition in contemporary orthography. 
 
-## Training and evaluation data
+The original corpus creators applied some corrections to the modern versions (see Jurish et al. 2013). For our use of the corpus, we further improved the quality of the normalized part of the corpus by enforcing spellings that accord to the German orthography reform (post 1996) and by applying selected rules of the [LanguageTool](https://pypi.org/project/language-tool-python/) and custom replacements to remove some errors and inconsistencies. We plan to publish the corpus as a dataset on the Huggingface Hub in the future.  
 
-More information needed
+The training set contains 96 documents with 4.6M source tokens, the dev and test set contain 13 documents (405K tokens) and 12 documents (381K tokens), respectively.
 
 ## Training procedure
 
@@ -77,7 +77,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 10 (published model: 8 epochs)
 
 ### Framework versions