add instruct

examples/libritts/cosyvoice/local/prepare_data.py

@@ -40,6 +40,11 @@ def main():
     with open('{}/spk2utt'.format(args.des_dir), 'w') as f:
         for k, v in spk2utt.items():
             f.write('{} {}\n'.format(k, ' '.join(v)))
+    if args.instruct is True:
+        with open('{}/instruct'.format(args.des_dir), 'w') as f:
+            for k, v in utt2text.items():
+                # NOTE in CosyVoice3, we add instruct in sequence
+                f.write('{} You are a helpful assistant.<|endofprompt|>\n'.format(k, v))
     return
 
 
@@ -49,7 +54,9 @@ if __name__ == "__main__":
                         type=str)
     parser.add_argument('--des_dir',
                         type=str)
-    parser.add_argument('--ref_model',
-                        type=str)
+    parser.add_argument('--instruct',
+                        action='store_true',
+                        default=False,
+                        help='create instruct file or not')
     args = parser.parse_args()
     main()

examples/libritts/cosyvoice3/run.sh

@@ -20,7 +20,7 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
   echo "Data preparation, prepare wav.scp/text/utt2spk/spk2utt"
   for x in train-clean-100 train-clean-360 train-other-500 dev-clean dev-other test-clean test-other; do
     mkdir -p data/$x
-    python local/prepare_data.py --src_dir $data_dir/LibriTTS/$x --des_dir data/$x
+    python local/prepare_data.py --src_dir $data_dir/LibriTTS/$x --des_dir data/$x --instruct
   done
 fi
 
@@ -46,6 +46,7 @@ if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
     mkdir -p data/$x/parquet
     tools/make_parquet_list.py --num_utts_per_parquet 1000 \
       --num_processes 10 \
+      --instruct \
       --src_dir data/$x \
       --des_dir data/$x/parquet
   done