Upload 13 files

HuBERT-SER/.gitignore

@@ -0,0 +1,133 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+.idea
+*.tmp.py
+.DS_Store
+.DS_store

HuBERT-SER/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

HuBERT-SER/README.md

@@ -0,0 +1,67 @@
+# HuBERT-SER
+
+
+This repository consists of models, scripts, and notebooks that help you to use all the benefits of HuBERT 2.0 in your research. In the following, I'll show you how to train speech tasks in your dataset and how to use the pretrained models.
+
+
+### Training - CMD
+
+```pwsh
+python "HuBERT-SER\run_wav2vec_clf.py" --pooling_mode="mean" --model_name_or_path="facebook/hubert-large-ll60k" --model_mode="hubert" --output_dir="path\to\output" --cache_dir="path\to\cache" --train_file="dataset\train.csv" --validation_file="dataset\eval.csv" --test_file="dataset\test.csv" --per_device_train_batch_size=4 --per_device_eval_batch_size=4 --gradient_accumulation_steps=2 --learning_rate=1e-4 --num_train_epochs=9.0 --evaluation_strategy='steps' --save_steps=100 --eval_steps=100 --logging_steps=100 --save_total_limit=2 --do_eval --do_train --freeze_feature_extractor
+```
+
+### Prediction
+
+```python
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import torchaudio
+from transformers import AutoConfig, Wav2Vec2FeatureExtractor
+from src.models import Wav2Vec2ForSpeechClassification, HubertForSpeechClassification
+
+model_name_or_path = "path/to/your-pretrained-model"
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+config = AutoConfig.from_pretrained(model_name_or_path)
+feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(model_name_or_path)
+sampling_rate = feature_extractor.sampling_rate
+
+model = HubertForSpeechClassification.from_pretrained(model_name_or_path).to(device)
+
+def speech_file_to_array_fn(path, sampling_rate):
+    speech_array, _sampling_rate = torchaudio.load(path)
+    resampler = torchaudio.transforms.Resample(_sampling_rate, sampling_rate)
+    speech = resampler(speech_array).squeeze().numpy()
+    return speech
+
+
+def predict(path, sampling_rate):
+    speech = speech_file_to_array_fn(path, sampling_rate)
+    inputs = feature_extractor(speech, sampling_rate=sampling_rate, return_tensors="pt", padding=True)
+    inputs = {key: inputs[key].to(device) for key in inputs}
+
+    with torch.no_grad():
+        logits = model(**inputs).logits
+
+    scores = F.softmax(logits, dim=1).detach().cpu().numpy()[0]
+    outputs = [{"Emotion": config.id2label[i], "Score": f"{round(score * 100, 3):.1f}%"} for i, score in
+               enumerate(scores)]
+    return outputs
+
+path = "./dataset/disgust.wav"
+outputs = predict(path, sampling_rate)
+print(outputs) 
+```
+
+Output:
+
+```bash
+[
+    {'Emotion': 'anger', 'Score': '0.0%'},
+    {'Emotion': 'disgust', 'Score': '99.2%'},
+    {'Emotion': 'fear', 'Score': '0.1%'},
+    {'Emotion': 'happiness', 'Score': '0.3%'},
+    {'Emotion': 'sadness', 'Score': '0.5%'}
+]
+```

HuBERT-SER/requirements.txt

@@ -0,0 +1,6 @@
+torch
+numpy
+git+https://github.com/huggingface/datasets.git
+git+https://github.com/huggingface/transformers.git
+torchaudio
+librosa

HuBERT-SER/run_wav2vec_clf.py

@@ -0,0 +1,491 @@
+import logging
+import os
+import sys
+from dataclasses import dataclass, field
+from typing import Any, Dict, List, Optional, Union
+
+from datasets import load_dataset, load_metric
+import numpy as np
+import torch
+import torchaudio
+
+import transformers
+from transformers import (
+    HfArgumentParser,
+    TrainingArguments,
+    EvalPrediction,
+    AutoConfig,
+    Wav2Vec2Processor,
+    Wav2Vec2FeatureExtractor,
+    is_apex_available,
+    set_seed,
+)
+from transformers.trainer_utils import get_last_checkpoint, is_main_process
+
+from src.models import Wav2Vec2ForSpeechClassification, HubertForSpeechClassification
+from src.collator import DataCollatorCTCWithPadding
+from src.trainer import CTCTrainer
+
+logger = logging.getLogger(__name__)
+MODEL_MODES = ["wav2vec", "hubert"]
+POOLING_MODES = ["mean", "sum", "max"]
+DELIMITERS = {"tab": "\t", "comma": ",", "pipe": "|"}
+
+
+@dataclass
+class ModelArguments:
+    """
+    Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.
+    """
+
+    model_name_or_path: str = field(
+        metadata={"help": "Path to pretrained model or model identifier from huggingface.co/models"}
+    )
+    model_mode: str = field(
+        default="wav2vec",
+        metadata={
+            "help": "Specifies the base model and must be from the following: " + ", ".join(MODEL_MODES)
+        },
+    )
+    pooling_mode: str = field(
+        default="mean",
+        metadata={
+            "help": "Specifies the reduction to apply to the output of Wav2Vec2 model and must be from the following: " + ", ".join(
+                POOLING_MODES)
+        },
+    )
+    config_name: Optional[str] = field(
+        default=None, metadata={"help": "Pretrained config name or path if not the same as model_name"}
+    )
+    feature_extractor_name: Optional[str] = field(
+        default=None, metadata={"help": "Pretrained feature_extractor name or path if not the same as model_name"}
+    )
+    cache_dir: Optional[str] = field(
+        default=None,
+        metadata={"help": "Where do you want to store the pretrained models downloaded from huggingface.co"},
+    )
+    freeze_feature_extractor: Optional[bool] = field(
+        default=True, metadata={"help": "Whether to freeze the feature extractor layers of the model."}
+    )
+    model_revision: str = field(
+        default="main",
+        metadata={"help": "The specific model version to use (can be a branch name, tag name or commit id)."},
+    )
+    use_auth_token: bool = field(
+        default=False,
+        metadata={
+            "help": "Will use the token generated when running `transformers-cli login` (necessary to use this script "
+                    "with private models)."
+        },
+    )
+
+
+@dataclass
+class DataTrainingArguments:
+    """
+    Arguments pertaining to what data we are going to input our model for training and eval.
+
+    Using `HfArgumentParser` we can turn this class
+    into argparse arguments to be able to specify them on
+    the command line.
+    """
+    train_file: Optional[str] = field(
+        default=None, metadata={"help": "The input training data file (a csv or JSON file)."}
+    )
+    validation_file: Optional[str] = field(
+        default=None,
+        metadata={"help": "An optional input evaluation data file to evaluate on (a csv or JSON file)."},
+    )
+    test_file: Optional[str] = field(
+        default=None,
+        metadata={"help": "An optional input evaluation data file to test on (a csv or JSON file)."},
+    )
+    input_column: Optional[str] = field(
+        default="path",
+        metadata={"help": "The name of the column in the datasets containing the audio path."},
+    )
+    target_column: Optional[str] = field(
+        default="emotion",
+        metadata={"help": "The name of the column in the datasets containing the labels."},
+    )
+    delimiter: Optional[str] = field(
+        default="tab",
+        metadata={
+            "help": "Specifies the character delimiting individual cells in the CSV data and must be from the following: " + ", ".join(
+                DELIMITERS.keys())
+        },
+    )
+    overwrite_cache: bool = field(
+        default=False, metadata={"help": "Overwrite the cached preprocessed datasets or not."}
+    )
+    preprocessing_num_workers: Optional[int] = field(
+        default=None,
+        metadata={"help": "The number of processes to use for the preprocessing."},
+    )
+    max_train_samples: Optional[int] = field(
+        default=None,
+        metadata={
+            "help": "For debugging purposes or quicker training, truncate the number of training examples to this "
+                    "value if set."
+        },
+    )
+    max_eval_samples: Optional[int] = field(
+        default=None,
+        metadata={
+            "help": "For debugging purposes or quicker training, truncate the number of validation examples to this "
+                    "value if set."
+        },
+    )
+    max_predict_samples: Optional[int] = field(
+        default=None,
+        metadata={
+            "help": "For debugging purposes or quicker training, truncate the number of prediction examples to this "
+                    "value if set."
+        },
+    )
+    min_duration_in_seconds: Optional[float] = field(
+        default=None,
+        metadata={"help": "Filters out examples less than specified. Defaults to no filtering."},
+    )
+    max_duration_in_seconds: Optional[float] = field(
+        default=None,
+        metadata={"help": "Filters out examples longer than specified. Defaults to no filtering."},
+    )
+
+    def __post_init__(self):
+        if self.train_file is None and self.validation_file is None:
+            raise ValueError("Need either a dataset name or a training/validation file.")
+        else:
+            extension = self.train_file.split(".")[-1]
+            assert extension in ["csv", "json"], "`train_file` should be a csv or a json file."
+            extension = self.validation_file.split(".")[-1]
+            assert extension in ["csv", "json"], "`validation_file` should be a csv or a json file."
+
+
+def main():
+    # See all possible arguments in src/transformers/training_args.py
+    # or by passing the --help flag to this script.
+    # We now keep distinct sets of args, for a cleaner separation of concerns.
+
+    parser = HfArgumentParser((ModelArguments, DataTrainingArguments, TrainingArguments))
+    if len(sys.argv) == 2 and sys.argv[1].endswith(".json"):
+        # If we pass only one argument to the script and it's the path to a json file,
+        # let's parse it to get our arguments.
+        model_args, data_args, training_args = parser.parse_json_file(json_file=os.path.abspath(sys.argv[1]))
+    else:
+        model_args, data_args, training_args = parser.parse_args_into_dataclasses()
+
+    # Detecting last checkpoint.
+    last_checkpoint = None
+    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
+        last_checkpoint = get_last_checkpoint(training_args.output_dir)
+        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
+            raise ValueError(
+                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
+                "Use --overwrite_output_dir to overcome."
+            )
+        elif last_checkpoint is not None:
+            logger.info(
+                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
+                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
+            )
+    logger.info(f"last_checkpoint: {last_checkpoint}")
+
+    # Setup logging
+    logging.basicConfig(
+        format="%(asctime)s - %(levelname)s - %(name)s -   %(message)s",
+        datefmt="%m/%d/%Y %H:%M:%S",
+        handlers=[logging.StreamHandler(sys.stdout)],
+    )
+    logger.setLevel(logging.INFO if is_main_process(training_args.local_rank) else logging.WARN)
+
+    # Log on each process the small summary:
+    logger.warning(
+        f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
+        + f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
+    )
+    # Set the verbosity to info of the Transformers logger (on main process only):
+    if is_main_process(training_args.local_rank):
+        transformers.utils.logging.set_verbosity_info()
+    logger.info("Training/evaluation parameters %s", training_args)
+
+    # Set seed before initializing model.
+    set_seed(training_args.seed)
+
+    # Loading a dataset from your local files.
+    # CSV/JSON training and evaluation files are needed.
+    data_files = {"train": data_args.train_file, "validation": data_args.validation_file}
+
+    # Get the test dataset: you can provide your own CSV/JSON test file (see below)
+    # when you use `do_predict` without specifying a GLUE benchmark task.
+    if training_args.do_predict:
+        if data_args.test_file is not None:
+            train_extension = data_args.train_file.split(".")[-1]
+            test_extension = data_args.test_file.split(".")[-1]
+            assert (
+                    test_extension == train_extension
+            ), "`test_file` should have the same extension (csv or json) as `train_file`."
+            data_files["test"] = data_args.test_file
+        else:
+            raise ValueError("Need a test file for `do_predict`.")
+
+    for key in data_files.keys():
+        logger.info(f"load a local file for {key}: {data_files[key]}")
+
+    if data_args.train_file.endswith(".csv"):
+        # Loading a dataset from local csv files
+        datasets = load_dataset(
+            "csv",
+            data_files=data_files,
+            delimiter=DELIMITERS.get(data_args.delimiter, "\t"),
+            cache_dir=model_args.cache_dir
+        )
+    else:
+        # Loading a dataset from local json files
+        datasets = load_dataset("json", data_files=data_files, cache_dir=model_args.cache_dir)
+
+    input_column_name = data_args.input_column
+    output_column_name = data_args.target_column
+
+    # Trying to have good defaults here, don't hesitate to tweak to your needs.
+    is_regression = datasets["train"].features[output_column_name].dtype in ["float32", "float64"]
+    if is_regression:
+        num_labels = 1
+        label_list = []
+        logger.info(f"*** A regression problem ***")
+    else:
+        # A useful fast method:
+        # https://huggingface.co/docs/datasets/package_reference/main_classes.html#datasets.Dataset.unique
+        label_list = datasets["train"].unique(output_column_name)
+        label_list.sort()  # Let's sort it for determinism
+        num_labels = len(label_list)
+
+        logger.info(f"*** A classification problem with {num_labels} classes ***")
+
+    # Load pretrained model and tokenizer
+    #
+    # Distributed training:
+    # The .from_pretrained methods guarantee that only one local process can concurrently
+    # download model & vocab.
+    config = AutoConfig.from_pretrained(
+        model_args.config_name if model_args.config_name else model_args.model_name_or_path,
+        num_labels=num_labels,
+        label2id={label: i for i, label in enumerate(label_list)},
+        id2label={i: label for i, label in enumerate(label_list)},
+        finetuning_task="wav2vec2_clf",
+        cache_dir=model_args.cache_dir,
+        revision=model_args.model_revision,
+        use_auth_token=True if model_args.use_auth_token else None,
+    )
+    setattr(config, 'pooling_mode', model_args.pooling_mode)
+
+    # tokenizer = Wav2Vec2CTCTokenizer.from_pretrained(model_args.model_name_or_path)
+    # feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(model_args.model_name_or_path)
+    # processor = Wav2Vec2Processor.from_pretrained(
+    #     model_args.processor_name if model_args.processor_name else model_args.model_name_or_path,
+    #     cache_dir=model_args.cache_dir,
+    #     revision=model_args.model_revision,
+    #     use_auth_token=True if model_args.use_auth_token else None,
+    # )
+    feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(
+        model_args.feature_extractor_name if model_args.feature_extractor_name else model_args.model_name_or_path,
+        cache_dir=model_args.cache_dir,
+        revision=model_args.model_revision,
+        use_auth_token=True if model_args.use_auth_token else None,
+    )
+    target_sampling_rate = feature_extractor.sampling_rate
+
+    if model_args.model_mode == "wav2vec":
+        model = Wav2Vec2ForSpeechClassification.from_pretrained(
+            model_args.model_name_or_path,
+            from_tf=bool(".ckpt" in model_args.model_name_or_path),
+            config=config,
+            cache_dir=model_args.cache_dir,
+            revision=model_args.model_revision,
+            use_auth_token=True if model_args.use_auth_token else None,
+        )
+    elif model_args.model_mode == "hubert":
+        model = HubertForSpeechClassification.from_pretrained(
+            model_args.model_name_or_path,
+            from_tf=bool(".ckpt" in model_args.model_name_or_path),
+            config=config,
+            cache_dir=model_args.cache_dir,
+            revision=model_args.model_revision,
+            use_auth_token=True if model_args.use_auth_token else None,
+        )
+    else:
+        raise ValueError("--model_mode does not exist in predefined modes: " + ",".join(MODEL_MODES))
+
+    if model_args.freeze_feature_extractor:
+        model.freeze_feature_extractor()
+
+    # NOTE: Duration controller for the future `min_duration_in_seconds` `max_duration_in_seconds`
+    # data_args.min_duration_in_seconds, data_args.max_duration_in_seconds
+
+    def speech_file_to_array_fn(path):
+        speech_array, sampling_rate = torchaudio.load(path)
+        resampler = torchaudio.transforms.Resample(sampling_rate, target_sampling_rate)
+        speech = resampler(speech_array).squeeze().numpy()
+        return speech
+
+    def label_to_id(label, label_list):
+
+        if len(label_list) > 0:
+            return label_list.index(label) if label in label_list else -1
+
+        return label
+
+    def preprocess_function(examples):
+        speech_list = [speech_file_to_array_fn(path) for path in examples[input_column_name]]
+        target_list = [label_to_id(label, label_list) for label in examples[output_column_name]]
+
+        result = feature_extractor(speech_list, sampling_rate=target_sampling_rate)
+        result["labels"] = list(target_list)
+
+        return result
+
+    if training_args.do_train:
+        if "train" not in datasets:
+            raise ValueError("--do_train requires a train dataset")
+
+        train_dataset = datasets["train"]
+
+        if data_args.max_train_samples is not None:
+            train_dataset = train_dataset.select(range(data_args.max_train_samples))
+
+        train_dataset = train_dataset.map(
+            preprocess_function,
+            batched=True,
+            load_from_cache_file=not data_args.overwrite_cache
+        )
+        logger.info(f"Split sizes: {len(train_dataset)} train")
+
+    if training_args.do_eval:
+        if "validation" not in datasets:
+            raise ValueError("--do_eval requires a validation dataset")
+
+        eval_dataset = datasets["validation"]
+
+        if data_args.max_eval_samples is not None:
+            eval_dataset = eval_dataset.select(range(data_args.max_eval_samples))
+
+        eval_dataset = eval_dataset.map(
+            preprocess_function,
+            batched=True,
+            load_from_cache_file=not data_args.overwrite_cache
+        )
+        logger.info(f"Split sizes: {len(eval_dataset)} validation")
+
+    if training_args.do_predict:
+        if "test" not in datasets:
+            raise ValueError("--do_predict requires a test dataset")
+
+        predict_dataset = datasets["test"]
+
+        if data_args.max_predict_samples is not None:
+            predict_dataset = predict_dataset.select(range(data_args.max_predict_samples))
+
+        predict_dataset = predict_dataset.map(
+            preprocess_function,
+            batched=True,
+            load_from_cache_file=not data_args.overwrite_cache
+        )
+        logger.info(f"Split sizes: {len(predict_dataset)} test.")
+
+    # Metric
+    # You can define your custom compute_metrics function. It takes an `EvalPrediction` object (a namedtuple with a
+    # predictions and label_ids field) and has to return a dictionary string to float.
+    def compute_metrics(p: EvalPrediction):
+        preds = p.predictions[0] if isinstance(p.predictions, tuple) else p.predictions
+        preds = np.squeeze(preds) if is_regression else np.argmax(preds, axis=1)
+
+        if is_regression:
+            return {"mse": ((preds - p.label_ids) ** 2).mean().item()}
+        else:
+            return {"accuracy": (preds == p.label_ids).astype(np.float32).mean().item()}
+
+    # Data collator
+    data_collator = DataCollatorCTCWithPadding(feature_extractor=feature_extractor, padding=True)
+
+    # Initialize our Trainer
+    trainer = CTCTrainer(
+        model=model,
+        data_collator=data_collator,
+        args=training_args,
+        compute_metrics=compute_metrics,
+        train_dataset=train_dataset if training_args.do_train else None,
+        eval_dataset=eval_dataset if training_args.do_eval else None,
+        tokenizer=feature_extractor,
+    )
+
+    # Training
+    if training_args.do_train:
+        if last_checkpoint is not None:
+            checkpoint = last_checkpoint
+        elif os.path.isdir(model_args.model_name_or_path):
+            checkpoint = model_args.model_name_or_path
+        else:
+            checkpoint = None
+
+        logger.info(f"*** Training from: {checkpoint} ***")
+        train_result = trainer.train(resume_from_checkpoint=checkpoint)
+        trainer.save_model()
+
+        # save the feature_extractor and the tokenizer
+        if is_main_process(training_args.local_rank):
+            feature_extractor.save_pretrained(training_args.output_dir)
+
+        metrics = train_result.metrics
+        max_train_samples = (
+            data_args.max_train_samples if data_args.max_train_samples is not None else len(train_dataset)
+        )
+        metrics["train_samples"] = min(max_train_samples, len(train_dataset))
+
+        trainer.log_metrics("train", metrics)
+        trainer.save_metrics("train", metrics)
+        trainer.save_state()
+
+    # Evaluation
+    results = {}
+    if training_args.do_eval:
+        logger.info("*** Evaluate ***")
+        metrics = trainer.evaluate()
+        max_eval_samples = data_args.max_eval_samples if data_args.max_eval_samples is not None else len(eval_dataset)
+        metrics["eval_samples"] = min(max_eval_samples, len(eval_dataset))
+
+        trainer.log_metrics("eval", metrics)
+        trainer.save_metrics("eval", metrics)
+
+    # Final test metrics
+    if training_args.do_predict:
+        logger.info("*** Test ***")
+
+        predict_dataset.remove_columns_(output_column_name)
+        predictions = trainer.predict(predict_dataset, metric_key_prefix="predict").predictions
+        predictions = np.squeeze(predictions) if is_regression else np.argmax(predictions, axis=1)
+
+        output_predict_file = os.path.join(training_args.output_dir, f"predict_results.txt")
+        if trainer.is_world_process_zero():
+            with open(output_predict_file, "w", encoding="utf-8") as writer:
+                logger.info(f"***** Predict results *****")
+                writer.write("index\tprediction\n")
+                for index, item in enumerate(predictions):
+                    if is_regression:
+                        writer.write(f"{index}\t{item:3.3f}\n")
+                    else:
+                        item = label_list[item]
+                        writer.write(f"{index}\t{item}\n")
+
+    # NOTE: Pushing to hub for future
+    # training_args.push_to_hub
+
+    return results
+
+
+def _mp_fn(index):
+    # For xla_spawn (TPUs)
+    main()
+
+
+if __name__ == "__main__":
+    main()

HuBERT-SER/src/collator.py

@@ -0,0 +1,58 @@
+from dataclasses import dataclass
+from typing import Dict, List, Optional, Union
+import torch
+
+import transformers
+from transformers import Wav2Vec2Processor, Wav2Vec2FeatureExtractor
+
+
+@dataclass
+class DataCollatorCTCWithPadding:
+    """
+    Data collator that will dynamically pad the inputs received.
+    Args:
+        feature_extractor (:class:`~transformers.Wav2Vec2FeatureExtractor`)
+            The feature_extractor used for proccessing the data.
+        padding (:obj:`bool`, :obj:`str` or :class:`~transformers.tokenization_utils_base.PaddingStrategy`, `optional`, defaults to :obj:`True`):
+            Select a strategy to pad the returned sequences (according to the model's padding side and padding index)
+            among:
+            * :obj:`True` or :obj:`'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
+              sequence if provided).
+            * :obj:`'max_length'`: Pad to a maximum length specified with the argument :obj:`max_length` or to the
+              maximum acceptable input length for the model if that argument is not provided.
+            * :obj:`False` or :obj:`'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of
+              different lengths).
+        max_length (:obj:`int`, `optional`):
+            Maximum length of the ``input_values`` of the returned list and optionally padding length (see above).
+        max_length_labels (:obj:`int`, `optional`):
+            Maximum length of the ``labels`` returned list and optionally padding length (see above).
+        pad_to_multiple_of (:obj:`int`, `optional`):
+            If set will pad the sequence to a multiple of the provided value.
+            This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability >=
+            7.5 (Volta).
+    """
+
+    feature_extractor: Wav2Vec2FeatureExtractor
+    padding: Union[bool, str] = True
+    max_length: Optional[int] = None
+    max_length_labels: Optional[int] = None
+    pad_to_multiple_of: Optional[int] = None
+    pad_to_multiple_of_labels: Optional[int] = None
+
+    def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
+        input_features = [{"input_values": feature["input_values"]} for feature in features]
+        label_features = [feature["labels"] for feature in features]
+
+        d_type = torch.long if isinstance(label_features[0], int) else torch.float
+
+        batch = self.feature_extractor.pad(
+            input_features,
+            padding=self.padding,
+            max_length=self.max_length,
+            pad_to_multiple_of=self.pad_to_multiple_of,
+            return_tensors="pt",
+        )
+
+        batch["labels"] = torch.tensor(label_features, dtype=d_type)
+
+        return batch

HuBERT-SER/src/modeling_outputs.py

@@ -0,0 +1,12 @@
+from dataclasses import dataclass
+from typing import Optional, Tuple
+import torch
+from transformers.file_utils import ModelOutput
+
+
+@dataclass
+class SpeechClassifierOutput(ModelOutput):
+    loss: Optional[torch.FloatTensor] = None
+    logits: torch.FloatTensor = None
+    hidden_states: Optional[Tuple[torch.FloatTensor]] = None
+    attentions: Optional[Tuple[torch.FloatTensor]] = None

HuBERT-SER/src/models.py

@@ -0,0 +1,222 @@
+import torch
+import torch.nn as nn
+from torch.nn import BCEWithLogitsLoss, CrossEntropyLoss, MSELoss
+
+from transformers.models.wav2vec2.modeling_wav2vec2 import (
+    Wav2Vec2PreTrainedModel,
+    Wav2Vec2Model
+)
+from transformers.models.hubert.modeling_hubert import (
+    HubertPreTrainedModel,
+    HubertModel
+)
+
+from src.modeling_outputs import SpeechClassifierOutput
+
+
+class Wav2Vec2ClassificationHead(nn.Module):
+    """Head for wav2vec classification task."""
+
+    def __init__(self, config):
+        super().__init__()
+        self.dense = nn.Linear(config.hidden_size, config.hidden_size)
+        self.dropout = nn.Dropout(config.final_dropout)
+        self.out_proj = nn.Linear(config.hidden_size, config.num_labels)
+
+    def forward(self, features, **kwargs):
+        x = features
+        x = self.dropout(x)
+        x = self.dense(x)
+        x = torch.tanh(x)
+        x = self.dropout(x)
+        x = self.out_proj(x)
+        return x
+
+
+class Wav2Vec2ForSpeechClassification(Wav2Vec2PreTrainedModel):
+    def __init__(self, config):
+        super().__init__(config)
+        self.num_labels = config.num_labels
+        self.pooling_mode = config.pooling_mode
+        self.config = config
+
+        self.wav2vec2 = Wav2Vec2Model(config)
+        self.classifier = Wav2Vec2ClassificationHead(config)
+
+        self.init_weights()
+
+    def freeze_feature_extractor(self):
+        self.wav2vec2.feature_extractor._freeze_parameters()
+
+    def merged_strategy(
+            self,
+            hidden_states,
+            mode="mean"
+    ):
+        if mode == "mean":
+            outputs = torch.mean(hidden_states, dim=1)
+        elif mode == "sum":
+            outputs = torch.sum(hidden_states, dim=1)
+        elif mode == "max":
+            outputs = torch.max(hidden_states, dim=1)[0]
+        else:
+            raise Exception(
+                "The pooling method hasn't been defined! Your pooling mode must be one of these ['mean', 'sum', 'max']")
+
+        return outputs
+
+    def forward(
+            self,
+            input_values,
+            attention_mask=None,
+            output_attentions=None,
+            output_hidden_states=None,
+            return_dict=None,
+            labels=None,
+    ):
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+        outputs = self.wav2vec2(
+            input_values,
+            attention_mask=attention_mask,
+            output_attentions=output_attentions,
+            output_hidden_states=output_hidden_states,
+            return_dict=return_dict,
+        )
+        hidden_states = outputs[0]
+        hidden_states = self.merged_strategy(hidden_states, mode=self.pooling_mode)
+        logits = self.classifier(hidden_states)
+
+        loss = None
+        if labels is not None:
+            if self.config.problem_type is None:
+                if self.num_labels == 1:
+                    self.config.problem_type = "regression"
+                elif self.num_labels > 1 and (labels.dtype == torch.long or labels.dtype == torch.int):
+                    self.config.problem_type = "single_label_classification"
+                else:
+                    self.config.problem_type = "multi_label_classification"
+
+            if self.config.problem_type == "regression":
+                loss_fct = MSELoss()
+                loss = loss_fct(logits.view(-1, self.num_labels), labels)
+            elif self.config.problem_type == "single_label_classification":
+                loss_fct = CrossEntropyLoss()
+                loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
+            elif self.config.problem_type == "multi_label_classification":
+                loss_fct = BCEWithLogitsLoss()
+                loss = loss_fct(logits, labels)
+
+        if not return_dict:
+            output = (logits,) + outputs[2:]
+            return ((loss,) + output) if loss is not None else output
+
+        return SpeechClassifierOutput(
+            loss=loss,
+            logits=logits,
+            hidden_states=outputs.hidden_states,
+            attentions=outputs.attentions,
+        )
+
+
+class HubertClassificationHead(nn.Module):
+    """Head for hubert classification task."""
+
+    def __init__(self, config):
+        super().__init__()
+        self.dense = nn.Linear(config.hidden_size, config.hidden_size)
+        self.dropout = nn.Dropout(config.final_dropout)
+        self.out_proj = nn.Linear(config.hidden_size, config.num_labels)
+
+    def forward(self, features, **kwargs):
+        x = features
+        x = self.dropout(x)
+        x = self.dense(x)
+        x = torch.tanh(x)
+        x = self.dropout(x)
+        x = self.out_proj(x)
+        return x
+
+
+class HubertForSpeechClassification(HubertPreTrainedModel):
+    def __init__(self, config):
+        super().__init__(config)
+        self.num_labels = config.num_labels
+        self.pooling_mode = config.pooling_mode
+        self.config = config
+
+        self.hubert = HubertModel(config)
+        self.classifier = HubertClassificationHead(config)
+
+        self.init_weights()
+
+    def freeze_feature_extractor(self):
+        self.hubert.feature_extractor._freeze_parameters()
+
+    def merged_strategy(
+            self,
+            hidden_states,
+            mode="mean"
+    ):
+        if mode == "mean":
+            outputs = torch.mean(hidden_states, dim=1)
+        elif mode == "sum":
+            outputs = torch.sum(hidden_states, dim=1)
+        elif mode == "max":
+            outputs = torch.max(hidden_states, dim=1)[0]
+        else:
+            raise Exception(
+                "The pooling method hasn't been defined! Your pooling mode must be one of these ['mean', 'sum', 'max']")
+
+        return outputs
+
+    def forward(
+            self,
+            input_values,
+            attention_mask=None,
+            output_attentions=None,
+            output_hidden_states=None,
+            return_dict=None,
+            labels=None,
+    ):
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+        outputs = self.hubert(
+            input_values,
+            attention_mask=attention_mask,
+            output_attentions=output_attentions,
+            output_hidden_states=output_hidden_states,
+            return_dict=return_dict,
+        )
+        hidden_states = outputs[0]
+        hidden_states = self.merged_strategy(hidden_states, mode=self.pooling_mode)
+        logits = self.classifier(hidden_states)
+
+        loss = None
+        if labels is not None:
+            if self.config.problem_type is None:
+                if self.num_labels == 1:
+                    self.config.problem_type = "regression"
+                elif self.num_labels > 1 and (labels.dtype == torch.long or labels.dtype == torch.int):
+                    self.config.problem_type = "single_label_classification"
+                else:
+                    self.config.problem_type = "multi_label_classification"
+
+            if self.config.problem_type == "regression":
+                loss_fct = MSELoss()
+                loss = loss_fct(logits.view(-1, self.num_labels), labels)
+            elif self.config.problem_type == "single_label_classification":
+                loss_fct = CrossEntropyLoss()
+                loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
+            elif self.config.problem_type == "multi_label_classification":
+                loss_fct = BCEWithLogitsLoss()
+                loss = loss_fct(logits, labels)
+
+        if not return_dict:
+            output = (logits,) + outputs[2:]
+            return ((loss,) + output) if loss is not None else output
+
+        return SpeechClassifierOutput(
+            loss=loss,
+            logits=logits,
+            hidden_states=outputs.hidden_states,
+            attentions=outputs.attentions,
+        )

HuBERT-SER/src/trainer.py

@@ -0,0 +1,65 @@
+from typing import Any, Dict, Union
+
+import torch
+from packaging import version
+from torch import nn
+from transformers import Trainer, is_apex_available, TrainingArguments
+
+if is_apex_available():
+    from apex import amp
+
+if version.parse(torch.__version__) >= version.parse("1.6"):
+    _is_native_amp_available = True
+    from torch.cuda.amp import autocast, GradScaler
+else:
+    _is_native_amp_available = False
+
+
+class CTCTrainer(Trainer):
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.use_amp = _is_native_amp_available and self.args.fp16
+        self.scaler = GradScaler() if self.use_amp else None
+
+    def training_step(self, model: nn.Module, inputs: Dict[str, Union[torch.Tensor, Any]]) -> torch.Tensor:
+        """
+        Perform a training step on a batch of inputs.
+
+        Subclass and override to inject custom behavior.
+
+        Args:
+            model (:obj:`nn.Module`):
+                The model to train.
+            inputs (:obj:`Dict[str, Union[torch.Tensor, Any]]`):
+                The inputs and targets of the model.
+
+                The dictionary will be unpacked before being fed to the model. Most models expect the targets under the
+                argument :obj:`labels`. Check your model's documentation for all accepted arguments.
+
+        Return:
+            :obj:`torch.Tensor`: The tensor with training loss on this batch.
+        """
+
+        model.train()
+        inputs = self._prepare_inputs(inputs)
+
+        if self.use_amp:
+            with autocast():
+                loss = self.compute_loss(model, inputs)
+        else:
+            loss = self.compute_loss(model, inputs)
+
+        if self.args.gradient_accumulation_steps > 1:
+            loss = loss / self.args.gradient_accumulation_steps
+
+        if self.use_amp:
+            self.scaler.scale(loss).backward()
+        elif self.use_apex:
+            with amp.scale_loss(loss, self.optimizer) as scaled_loss:
+                scaled_loss.backward()
+        elif self.deepspeed:
+            self.deepspeed.backward(loss)
+        else:
+            loss.backward()
+
+        return loss.detach()