Load a language model and decode with it during evaluation

Based on !346 (merged)

Closes #252 (closed)

docs/usage/train/config.md

@@ -90,7 +90,7 @@ folder/
 | `training.device.nb_gpu`   | Number of GPUs to train DAN. Set to `null` to use all GPUs available.                                                       | `int`  |         |
 | `training.device.force`    | Use a specific device if available. Use `cpu` to train on CPU (for debugging) or `cuda`/`cuda:$gpu_device` to train on GPU. | `str`  |         |
 
-- To train on several GPUs, simply set the `training.device.use_ddp` parameter to `True`. By default, the model will use all available GPUs. To restrict access to fewer GPUs, one can modify the `training.device.nb_gpu` parameter.
+To train on several GPUs, simply set the `training.device.use_ddp` parameter to `True`. By default, the model will use all available GPUs. To restrict access to fewer GPUs, one can modify the `training.device.nb_gpu` parameter.
 
 ### Optimizers
 
@@ -107,7 +107,7 @@ folder/
 | `training.validation.eval_on_valid_interval` | Interval (in epochs) to evaluate during training.                          | `int`  | `5`     |
 | `training.validation.set_name_focus_metric`  | Dataset to focus on to select best weights.                                | `str`  |         |
 
-- During the validation stage, the batch size is set to 1. This avoids problems associated with image sizes that can be very different inside batches and lead to significant padding, resulting in performance degradations.
+During the validation stage, the batch size is set to 1. This avoids problems associated with image sizes that can be very different inside batches and lead to significant padding, resulting in performance degradations.
 
 ### Metrics