zchen/b2txt25
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

switch from .txt to .csv

Browse Source
This commit is contained in:
nckcard
2025-07-06 21:52:59 -07:00
parent 4ee016b032
commit d83bcc0976
5 changed files with 1436 additions and 1439 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
model_training/evaluate_model.py
View File

@@ -1,7 +1,7 @@
import os
import sys
import torch
import numpy as np
import pandas as pd
import redis
from omegaconf import OmegaConf
import time
@@ -262,13 +262,8 @@ if eval_type == 'val':
print(f'Aggregate Word Error Rate (WER): {100 * total_edit_distance / total_true_length:.2f}%')
# write predicted sentences to a text file. put a timestamp in the filename (YYYYMMDD_HHMMSS)
output_file = os.path.join(model_path, f'baseline_rnn_{eval_type}_predicted_sentences_{time.strftime("%Y%m%d_%H%M%S")}.txt')
with open(output_file, 'w') as f:
for i in range(len(lm_results['pred_sentence'])):
if i < len(lm_results['pred_sentence']) - 1:
# write sentence + newline
f.write(f"{remove_punctuation(lm_results['pred_sentence'][i])}\n")
else:
# don't add a newline at the end of the last sentence
f.write(f"{remove_punctuation(lm_results['pred_sentence'][i])}")
# write predicted sentences to a csv file. put a timestamp in the filename (YYYYMMDD_HHMMSS)
output_file = os.path.join(model_path, f'baseline_rnn_{eval_type}_predicted_sentences_{time.strftime("%Y%m%d_%H%M%S")}.csv')
ids = [i for i in range(len(lm_results['pred_sentence']))]
df_out = pd.DataFrame({'id': ids, 'text': lm_results['pred_sentence']})
df_out.to_csv(output_file, index=False)