remove eval from readme

readme.md

@@ -76,11 +76,6 @@ Train using the provided train script:
     poetry run train \
     --config_path="PATH_TO_CONFIG_FILE"
 
-## Evaluation
-Evaluation metrics are computed during training and are serialized with the checkpoints.
-
-TODO: manual evaluation script / access to the evaluation metrics?
-
 ## Inference
 The `config.yaml` also includes a section for inference. 
 To run inference on a single audio file, run:
@@ -90,4 +85,4 @@ To run inference on a single audio file, run:
     --file_path="PATH_TO_AUDIO_FILE" \
     --target_path="PATH_TO_TARGET_FILE"
 
-Target path is optional. If not specified, the recognized text will be printed to the console. Otherwise, a wer will be computed.
+Target path is optional. If not specified, the recognized text will be printed to the console. Otherwise, a wer will be computed.