fix the data type

app.py

@@ -1,6 +1,5 @@
 import evaluate
 from evaluate.utils import launch_gradio_widget
 
-
 module = evaluate.load("xu1998hz/sescore")
-launch_gradio_widget(module)
+launch_gradio_widget(module)

requirements.txt

@@ -1,3 +1,3 @@
 git+https://github.com/huggingface/evaluate@main
-gdown
 unbabel-comet
+torch

sescore.py

@@ -107,8 +107,8 @@ class SEScore(evaluate.Metric):
             inputs_description=_KWARGS_DESCRIPTION,
             # This defines the format of each prediction and reference
             features=datasets.Features({
-                'predictions': datasets.Value('int64'),
-                'references': datasets.Value('int64'),
+                'predictions': datasets.Value("string", id="sequence"),
+                'references': datasets.Value("string", id="sequence"),
             }),
             # Homepage of the module for documentation
             homepage="http://module.homepage",
@@ -121,23 +121,20 @@ class SEScore(evaluate.Metric):
         """download SEScore checkpoints to compute the scores"""
         # Download SEScore checkpoint
         from comet import load_from_checkpoint
-        import gdown
         import os
         from huggingface_hub import snapshot_download
         # initialize roberta into str2encoder
         comet.encoders.str2encoder['RoBERTa'] = robertaEncoder
-        # url = "https://drive.google.com/uc?id=1QgMP_Y4QCbvDMTeVacYt0J76OYvwWK9V&export=download&confirm=true"
-        # output = 'sescore_ckpt.gz'
-        # gdown.download(url, output, quiet=False)
-        # cmd = 'tar -xvf sescore_ckpt.gz'
-        # os.system(cmd)
         destination = snapshot_download(repo_id="xu1998hz/sescore_english_mt", revision="main")
         self.scorer = load_from_checkpoint(f'{destination}/checkpoint/sescore_english_mt.ckpt')
 
     def _compute(self, predictions, references, gpus=None, progress_bar=False):
         if gpus is None:
             gpus = 1 if torch.cuda.is_available() else 0
+
         data = {"src": references, "mt": predictions}
+        print(data)
         data = [dict(zip(data, t)) for t in zip(*data.values())]
+        print(data)
         scores, mean_score = self.scorer.predict(data, gpus=gpus, progress_bar=progress_bar)
         return {"mean_score": mean_score, "scores": scores}