Update precommit CI action to latest version

.github/workflows/pre-commit.yml

@@ -12,5 +12,5 @@ jobs:
       - uses: actions/checkout@v2
       - uses: actions/setup-python@v2
         with:
-          python-version: '3.8'
-      - uses: pre-commit/action@v2.0.3
+          python-version: '3.12'
+      - uses: pre-commit/action@v3.0.1

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v2.5.0  # Use the ref you want to point at
+    rev: v5.0.0  # Use the ref you want to point at
     hooks:
       - id: trailing-whitespace
         types: [file, text]
@@ -21,7 +21,7 @@ repos:
         types: [python]
         additional_dependencies: ['click==8.0.4']
   - repo: https://github.com/PyCQA/flake8
-    rev: 3.7.9
+    rev: 7.0.0
     hooks:
       - id: flake8
         types: [python]

benchmarks/CL_MASR/analyze_logs.py

@@ -373,7 +373,7 @@ def plot_wer(
             plt.xticks(range(len(locales)), locales, rotation=90)
             if xlabel is not None:
                 plt.xlabel(xlabel)
-            plt.ylabel("WER (\%)" if usetex else "WER (%)")  # noqa: W605
+            plt.ylabel("WER (\\%)" if usetex else "WER (%)")  # noqa: W605
             fig.tight_layout()
             plt.savefig(output_image, bbox_inches="tight")
             plt.close()
@@ -851,7 +851,7 @@ def hex_to_rgb(hex_color: "str") -> "Tuple":
                 f"{name.lower().replace(' ', '_')}.{args.format}",
             ),
             xlabel=None,
-            ylabel=f"{name} (\%)"
+            ylabel=f"{name} (\\%)"
             if args.usetex
             else f"{name} (%)",  # noqa: W605
             xticks=["base"] + [f"L{i}" for i in range(1, 1 + len(new_locales))],

benchmarks/CL_MASR/common_voice_prepare.py

@@ -111,7 +111,7 @@ def prepare_common_voice(
     _LOGGER.info(
         "----------------------------------------------------------------------",
     )
-    _LOGGER.info(f"Merging TSV files...")
+    _LOGGER.info("Merging TSV files...")
     for split, max_duration in zip(_SPLITS, max_durations):
         tsv_files = [
             os.path.join(data_folder, locale, f"{split}_with_duration.tsv")
@@ -126,7 +126,7 @@ def prepare_common_voice(
     _LOGGER.info(
         "----------------------------------------------------------------------",
     )
-    _LOGGER.info(f"Creating data manifest CSV files...")
+    _LOGGER.info("Creating data manifest CSV files...")
     for split in _SPLITS:
         preprocess_tsv_file(
             os.path.join(data_folder, f"{split}_with_duration.tsv"),

benchmarks/CL_MASR/wavlm/pretrain.py

@@ -341,7 +341,7 @@ def train(hparams, run_opts):
 
     # Testing
     test(
-        hparams, run_opts, hparams["locales"], f"wer_test.txt",
+        hparams, run_opts, hparams["locales"], "wer_test.txt",
     )
 
 

benchmarks/CL_MASR/wavlm/train_agem.py

@@ -431,7 +431,7 @@ def train(hparams, run_opts):
 
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/CL_MASR/wavlm/train_der.py

@@ -363,7 +363,7 @@ def train(hparams, run_opts):
 
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     replay_buffer = []

benchmarks/CL_MASR/wavlm/train_er.py

@@ -306,7 +306,7 @@ def train(hparams, run_opts):
 
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/CL_MASR/wavlm/train_ewc.py

@@ -417,7 +417,7 @@ def train(hparams, run_opts):
 
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/CL_MASR/wavlm/train_ft.py

@@ -305,7 +305,7 @@ def train(hparams, run_opts):
 
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/CL_MASR/wavlm/train_joint.py

@@ -305,7 +305,7 @@ def train(hparams, run_opts):
 
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales
@@ -358,7 +358,7 @@ def train(hparams, run_opts):
         hparams,
         run_opts,
         hparams["base_locales"] + hparams["new_locales"],
-        f"wer_test_after.txt",
+        "wer_test_after.txt",
     )
 
 

benchmarks/CL_MASR/wavlm/train_l2p.py

@@ -374,7 +374,7 @@ def train(hparams, run_opts):
 
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/CL_MASR/wavlm/train_lwf.py

@@ -335,7 +335,7 @@ def train(hparams, run_opts):
 
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/CL_MASR/wavlm/train_mas.py

@@ -421,7 +421,7 @@ def train(hparams, run_opts):
 
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/CL_MASR/wavlm/train_pb.py

@@ -398,7 +398,7 @@ def train(hparams, run_opts):
 
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/CL_MASR/wavlm/train_pnn.py

@@ -309,7 +309,7 @@ def train(hparams, run_opts):
 
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/CL_MASR/whisper/model.py

@@ -277,7 +277,7 @@ def generate(
         if forced_decoder_locale is None:
             # Compute most likely language token IDs
             all_lang_tokens = [
-                f"<|{l}|>" for l in self.tokenizer.supported_languages
+                f"<|{lang}|>" for lang in self.tokenizer.supported_languages
             ]
             all_lang_tokens_ids = self.tokenizer.convert_tokens_to_ids(
                 all_lang_tokens
@@ -383,8 +383,8 @@ def _greedy_search(
             alive_mask_unchanged = gen_token_ids != endoftext_id
             if not alive_mask_unchanged.all():
                 alive_mask[
-                    alive_mask == True
-                ] = alive_mask_unchanged  # noqa: E712
+                    alive_mask == True  # noqa: E712
+                ] = alive_mask_unchanged
                 if not alive_mask.any():
                     break
                 # B* x S x F
@@ -567,8 +567,8 @@ def _beam_search(
                 alive_mask_unchanged = end_idxes < beam_size
                 if not alive_mask_unchanged.all():
                     alive_mask[
-                        alive_mask == True
-                    ] = alive_mask_unchanged  # noqa: E712
+                        alive_mask == True  # noqa: E712
+                    ] = alive_mask_unchanged
                     if not alive_mask.any():
                         break
                     # N x B* x S x F

benchmarks/CL_MASR/whisper/train_agem.py

@@ -452,7 +452,7 @@ def train(hparams, run_opts):
     """
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/CL_MASR/whisper/train_der.py

@@ -409,7 +409,7 @@ def train(hparams, run_opts):
     """
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     replay_buffer = []

benchmarks/CL_MASR/whisper/train_er.py

@@ -332,7 +332,7 @@ def train(hparams, run_opts):
     """
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/CL_MASR/whisper/train_ewc.py

@@ -454,7 +454,7 @@ def train(hparams, run_opts):
     """
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/CL_MASR/whisper/train_ft.py

@@ -331,7 +331,7 @@ def train(hparams, run_opts):
     """
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/CL_MASR/whisper/train_joint.py

@@ -332,7 +332,7 @@ def train(hparams, run_opts):
     """
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales
@@ -413,7 +413,7 @@ def train(hparams, run_opts):
         hparams,
         run_opts,
         hparams["base_locales"] + hparams["new_locales"],
-        f"wer_test_after.txt",
+        "wer_test_after.txt",
     )
 
 

benchmarks/CL_MASR/whisper/train_l2p.py

@@ -403,7 +403,7 @@ def train(hparams, run_opts):
     """
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/CL_MASR/whisper/train_lwf.py

@@ -368,7 +368,7 @@ def train(hparams, run_opts):
     """
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/CL_MASR/whisper/train_mas.py

@@ -456,7 +456,7 @@ def train(hparams, run_opts):
     """
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/CL_MASR/whisper/train_pb.py

@@ -422,7 +422,7 @@ def train(hparams, run_opts):
 
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/CL_MASR/whisper/train_pnn.py

@@ -334,7 +334,7 @@ def train(hparams, run_opts):
     """
     # Testing
     test(
-        hparams, run_opts, hparams["base_locales"], f"wer_test_before.txt",
+        hparams, run_opts, hparams["base_locales"], "wer_test_before.txt",
     )
 
     # Train on new locales

benchmarks/DASB/IEMOCAP/iemocap_prepare.py

@@ -271,7 +271,7 @@ def load_utterInfo(inputFile):
     # [START_TIME - END_TIME] TURN_NAME EMOTION [V, A, D]
     # [V, A, D] means [Valence, Arousal, Dominance]
     pattern = re.compile(
-        "[\[]*[0-9]*[.][0-9]*[ -]*[0-9]*[.][0-9]*[\]][\t][a-z0-9_]*[\t][a-z]{3}[\t][\[][0-9]*[.][0-9]*[, ]+[0-9]*[.][0-9]*[, ]+[0-9]*[.][0-9]*[\]]",
+        "[\[]*[0-9]*[.][0-9]*[ -]*[0-9]*[.][0-9]*[\]][\t][a-z0-9_]*[\t][a-z]{3}[\t][\[][0-9]*[.][0-9]*[, ]+[0-9]*[.][0-9]*[, ]+[0-9]*[.][0-9]*[\]]",  # noqa
         re.IGNORECASE,
     )  # noqa
     with open(inputFile, "r") as myfile:

benchmarks/DASB/Libri2Mix/separation/conformer/train_continuous_ssl.py

@@ -372,7 +372,7 @@ def on_stage_end(self, stage, stage_loss, epoch=None):
     )
     hparams["train_logger"].log_stats(
         stats_meta={
-            f"SSL parameters/buffers (M)": f"{ssl_params / 1e6:.2f}",
+            "SSL parameters/buffers (M)": f"{ssl_params / 1e6:.2f}",
             "Model parameters/buffers (M)": f"{model_params / 1e6:.2f}",
         },
     )

benchmarks/DASB/Libri2Mix/separation/conformer/train_dac.py

@@ -128,7 +128,7 @@ def toks_to_sig(self, toks):
     )
     hparams["train_logger"].log_stats(
         stats_meta={
-            f"Codec parameters/buffers (M)": f"{codec_params / 1e6:.2f}",
+            "Codec parameters/buffers (M)": f"{codec_params / 1e6:.2f}",
             "Model parameters/buffers (M)": f"{model_params / 1e6:.2f}",
         },
     )

benchmarks/DASB/Libri2Mix/separation/conformer/train_discrete_ssl.py

@@ -155,7 +155,7 @@ def toks_to_sig(self, toks):
     )
     hparams["train_logger"].log_stats(
         stats_meta={
-            f"Codec parameters/buffers (M)": f"{codec_params / 1e6:.2f}",
+            "Codec parameters/buffers (M)": f"{codec_params / 1e6:.2f}",
             "Model parameters/buffers (M)": f"{model_params / 1e6:.2f}",
         },
     )

benchmarks/DASB/Libri2Mix/separation/conformer/train_encodec.py

@@ -376,7 +376,7 @@ def on_stage_end(self, stage, stage_loss, epoch=None):
     )
     hparams["train_logger"].log_stats(
         stats_meta={
-            f"Codec parameters/buffers (M)": f"{codec_params / 1e6:.2f}",
+            "Codec parameters/buffers (M)": f"{codec_params / 1e6:.2f}",
             "Model parameters/buffers (M)": f"{model_params / 1e6:.2f}",
         },
     )

benchmarks/DASB/Libri2Mix/separation/conformer/train_speech_tokenizer.py

@@ -121,7 +121,7 @@ def toks_to_sig(self, toks):
     )
     hparams["train_logger"].log_stats(
         stats_meta={
-            f"Codec parameters/buffers (M)": f"{codec_params / 1e6:.2f}",
+            "Codec parameters/buffers (M)": f"{codec_params / 1e6:.2f}",
             "Model parameters/buffers (M)": f"{model_params / 1e6:.2f}",
         },
     )

benchmarks/DASB/Libri2Mix/separation/crdnn/train_continuous_ssl.py

@@ -372,7 +372,7 @@ def on_stage_end(self, stage, stage_loss, epoch=None):
     )
     hparams["train_logger"].log_stats(
         stats_meta={
-            f"SSL parameters/buffers (M)": f"{ssl_params / 1e6:.2f}",
+            "SSL parameters/buffers (M)": f"{ssl_params / 1e6:.2f}",
             "Model parameters/buffers (M)": f"{model_params / 1e6:.2f}",
         },
     )

benchmarks/DASB/Libri2Mix/separation/crdnn/train_dac.py

@@ -128,7 +128,7 @@ def toks_to_sig(self, toks):
     )
     hparams["train_logger"].log_stats(
         stats_meta={
-            f"Codec parameters/buffers (M)": f"{codec_params / 1e6:.2f}",
+            "Codec parameters/buffers (M)": f"{codec_params / 1e6:.2f}",
             "Model parameters/buffers (M)": f"{model_params / 1e6:.2f}",
         },
     )

benchmarks/DASB/Libri2Mix/separation/crdnn/train_discrete_ssl.py

@@ -155,7 +155,7 @@ def toks_to_sig(self, toks):
     )
     hparams["train_logger"].log_stats(
         stats_meta={
-            f"Codec parameters/buffers (M)": f"{codec_params / 1e6:.2f}",
+            "Codec parameters/buffers (M)": f"{codec_params / 1e6:.2f}",
             "Model parameters/buffers (M)": f"{model_params / 1e6:.2f}",
         },
     )