Add template files

README.md

@@ -0,0 +1,131 @@
+# SUPERB Submission Template
+
+Welcome to the [SUPERB benchmark](https://superbbenchmark.org)! SUPERB is a collection of benchmarking resources to evaluate the capability of a universal shared representation for speech processing. SUPERB consists of the following:
+
+1. A benchmark of ten speech processing tasks built on established public datasets
+2. A benchmark toolkit designed to evaluate and analyze pretrained model performance on various downstream tasks following the conventional evaluation protocols from speech communities
+3. A public leaderboard for submission and performance tracking on the benchmark
+
+SUPERB aims to offer the community a standard and comprehensive framework to train, evaluate, and compare the generalizability of universal speech representations on speech processing tasks. A universal speech representation can be leveraged to quickly adapt to diverse downstream tasks with minimum architectural change and downstream fine-tuning, so as to reduce the model development cycle time for new tasks. To emphasize on evaluating the quality of the learned universal representation, SUPERB puts an explicit constraint on the downstream model and limits its parameter size.
+
+The ultimate goal of SUPERB is to democratize the advancement in speech processing with powerful, generalizable, and reusable speech representations. SUPERB is a long-term maintained and continuously developing project. As we are gradually releasing new tasks and opening new tracks, we invite researchers to participate in the challenge and advance the research frontier together.
+
+This repository can be used to generate a template so you can submit your predictions for evaluation on [the leaderboard](https://huggingface.co/spaces/superb/superb-leaderboard).
+
+## Quickstart
+
+### 1. Create an account and organisation on the Hugging Face Hub
+
+First create an account on the Hugging Face Hub and you can sign up [here](https://huggingface.co/join) if you haven't already! Next, create a a new organisation for your submissions and invite the following benchmark organisers join it:
+
+* Shu-wen (Leo) Yang: [leo19941227](https://huggingface.co/leo19941227)
+
+### 2. Create a template repository on your machine
+
+The next step is to create a template repository on your local machine that contains various files and a CLI to help you validate and submit your pretrained models. The Hugging Face Hub uses [Git Large File Storage (LFS)](https://git-lfs.github.com) to manage large files, so first install it if you don't have it already. For example, on macOS you can run:
+
+```bash
+brew install git-lfs
+git lfs install
+```
+
+Next, run the following commands to create the repository. We recommend creating a Python virtual environment for the project, e.g. with Anaconda:
+
+```bash
+# Create and activate a virtual environment
+conda create -n superb python=3.8 && conda activate superb
+# Install the following libraries
+pip install cookiecutter huggingface-hub==0.0.16
+# Create the template repository
+cookiecutter git+https://huggingface.co/superb/superb-submission
+```
+
+This will ask you to specify your Hugging Face Hub username, password, organisation, and the name of the repository:
+
+```
+hf_hub_username [<huggingface>]:
+hf_hub_password [<password>]:
+hf_hub_organisation [superb-submissions]:
+repo_name [<my-superb-submissions>]:
+```
+
+This will trigger the following steps:
+
+1. Create a private dataset repository on the Hugging Face Hub under `{hf_hub_organisation}/{repo_name}`
+2. Clone the repository to your local machine
+3. Add various template files, commit them locally to the repository, and push them to the Hub
+
+The resulting repository should have the following structure:
+
+```
+my-superb-submission
+├── LICENSE
+├── README.md               <- The README with submission instructions
+├── cli.py                  <- The CLI for validating predictions etc
+└── requirements.txt        <- The requirements file for the submissions
+```
+
+### 3. Install the dependencies
+
+The final step is to install the project's dependencies:
+
+```bash
+# Navigate to the template repository
+cd my-superb-submission
+# Install dependencies
+python -m pip install -r requirements.txt
+```
+
+That's it! You're now all set to start pretraining your speech models - see the instructions below on how to submit them to the Hub.
+
+
+## Submitting to the leaderboard
+
+To make a submission to the [leaderboard](https://huggingface.co/spaces/superb/superb-leaderboard)), there are three main steps:
+
+1. Generate predictions on the unlabeled test set of each task
+2. Validate the predictions are compatible with the evaluation framework
+3. Push the predictions to the Hub!
+
+See the instructions below for more details.
+
+### Rules
+
+1. To prevent overfitting to the public leaderboard, we only evaluate **one submission per week**. You can push predictions to the Hub as many times as you wish, but we will only evaluate the most recent commit in a given week. 
+2. Transfer or meta-learning using other datasets, including further pre-training on other corpora, is allowed.
+3. Use of unlabeled test data is allowed, as is it always available in the applied setting. For example, further pre-training using the unlabeled data for a task would be permitted.
+4. Systems may be augmented with information retrieved from the internet, e.g. via automated web searches.
+
+### Submission file format
+
+### Validate your submission
+
+To ensure that your submission files are correctly formatted, run the following command from the root of the repository:
+
+```
+python cli.py validate
+```
+
+If everything is correct, you should see the following message:
+
+```
+All submission files validated! ✨ 🚀 ✨
+Now you can make a submission 🤗
+```
+
+### Push your submission to the Hugging Face Hub!
+
+The final step is to commit your files and push them to the Hub:
+
+```
+python cli.py submit
+```
+
+If there are no errors, you should see the following message:
+
+```
+Submission successful! 🎉 🥳 🎉
+Your submission will be fine-tuned and evaulated on Sunday 05 September 2021 ⏳
+```
+
+where the evaluation is run every Sunday and your results will be visible on the leaderboard.

cookiecutter.json

@@ -0,0 +1,6 @@
+{
+    "hf_hub_username": "huggingface",
+    "hf_hub_password": "password",
+    "hf_hub_organisation": "superb-submissions",
+    "repo_name": "my-superb-submission"
+}

hooks/post_gen_project.py

@@ -0,0 +1,6 @@
+import subprocess
+
+subprocess.call("git pull origin main".split())
+subprocess.call(["git", "add", "."])
+subprocess.call(["git", "commit", "-m", "Add template files"])
+subprocess.call("git push origin main".split())

hooks/pre_gen_project.py

@@ -0,0 +1,18 @@
+from huggingface_hub import HfApi, HfFolder, Repository
+
+hf_user = "{{cookiecutter.hf_hub_username}}"
+hf_password = "{{cookiecutter.hf_hub_password}}"
+hf_org = "{{cookiecutter.hf_hub_organisation}}"
+huggingface_token = HfApi().login(username=hf_user, password=hf_password)
+HfFolder.save_token(huggingface_token)
+
+repo_url = HfApi().create_repo(
+    token=huggingface_token,
+    name="{{cookiecutter.repo_name}}",
+    organization=hf_org,
+    exist_ok=True,
+    private=True
+)
+
+model_repo = Repository(local_dir=".", clone_from=repo_url, use_auth_token=huggingface_token)
+model_repo.add_file("README.md")

{{cookiecutter.repo_name}}/.gitignore

@@ -0,0 +1,141 @@
+# 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/
+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/
+cover/
+
+# 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
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .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/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# Datasets file locks
+*.lock

{{cookiecutter.repo_name}}/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.

{{cookiecutter.repo_name}}/README.md

@@ -0,0 +1,58 @@
+---
+benchmark: superb
+type: model-upload
+submission_nme: none
+---
+
+# SUPERB submissions for {{cookiecutter.repo_name}}
+
+## Submitting to the leaderboard
+
+To make a submission to the [leaderboard](https://huggingface.co/spaces/superb/superb-leaderboard)), there are three main steps:
+
+1. Generate predictions on the unlabeled test set of each task
+2. Validate the predictions are compatible with the evaluation framework
+3. Push the predictions to the Hub!
+
+See the instructions below for more details.
+
+### Rules
+
+1. To prevent overfitting to the public leaderboard, we only evaluate **one submission per week**. You can push predictions to the Hub as many times as you wish, but we will only evaluate the most recent commit in a given week. 
+2. Transfer or meta-learning using other datasets, including further pre-training on other corpora, is allowed.
+3. Use of unlabeled test data is allowed, as is it always available in the applied setting. For example, further pre-training using the unlabeled data for a task would be permitted.
+4. Systems may be augmented with information retrieved from the internet, e.g. via automated web searches.
+
+### Submission file format
+
+### Validate your submission
+
+To ensure that your submission files are correctly formatted, run the following command from the root of the repository:
+
+```
+python cli.py validate
+```
+
+If everything is correct, you should see the following message:
+
+```
+All submission files validated! ✨ 🚀 ✨
+Now you can make a submission 🤗
+```
+
+### Push your submission to the Hugging Face Hub!
+
+The final step is to commit your files and push them to the Hub:
+
+```
+python cli.py submit
+```
+
+If there are no errors, you should see the following message:
+
+```
+Submission successful! 🎉 🥳 🎉
+Your submission will be fine-tuned and evaulated on Sunday 05 September 2021 ⏳
+```
+
+where the evaluation is run every Sunday and your results will be visible on the leaderboard.

{{cookiecutter.repo_name}}/cli.py

@@ -0,0 +1,105 @@
+import datetime
+import re
+import subprocess
+from pathlib import Path
+
+import pandas as pd
+import typer
+from datasets import get_dataset_config_names, load_dataset
+
+CSV_SCHEMA = {
+    "banking_77": (5000, 2),
+    "overruling": (2350, 2),
+    "semiconductor_org_types": (449, 2),
+    "ade_corpus_v2": (5000, 2),
+    "twitter_complaints": (3399, 2),
+    "neurips_impact_statement_risks": (150, 2),
+    "systematic_review_inclusion": (2244, 2),
+    "terms_of_service": (5000, 2),
+    "tai_safety_research": (1639, 2),
+    "one_stop_english": (518, 2),
+    "tweet_eval_hate": (2966, 2),
+}
+
+app = typer.Typer()
+
+
+def _update_submission_name(submission_name: str):
+    replacement = ""
+    with open("README.md", "r") as f:
+        lines = f.readlines()
+
+    for line in lines:
+        if line.startswith("submission_name:"):
+            changes = re.sub(r"submission_name:.+", f"submission_name: {submission_name}", line)
+            replacement += changes
+        else:
+            replacement += line
+
+    with open("README.md", "w") as f:
+        f.write(replacement)
+
+
+@app.command()
+def validate():
+    # TODO(lewtun): Consider using great_expectations for the data validation
+    tasks = get_dataset_config_names("ought/raft")
+
+    # Check that all the expected files exist
+    prediction_files = list(Path("data").rglob("predictions.csv"))
+    mismatched_files = set(tasks).symmetric_difference(set([f.parent.name for f in prediction_files]))
+    if mismatched_files:
+        raise ValueError(f"Incorrect number of files! Expected {len(tasks)} files, but got {len(prediction_files)}.")
+
+    # Check all files have the expected shape (number of rows, number of columns)
+    # TODO(lewtun): Add a check for the specific IDs per file
+    shape_errors = []
+    column_errors = []
+    for prediction_file in prediction_files:
+        df = pd.read_csv(prediction_file)
+        incorrect_shape = df.shape != CSV_SCHEMA[prediction_file.parent.name]
+        if incorrect_shape:
+            shape_errors.append(prediction_file)
+        incorrect_columns = sorted(df.columns) != ["ID", "Label"]
+        if incorrect_columns:
+            column_errors.append(prediction_file)
+
+    if shape_errors:
+        raise ValueError(f"Incorrect CSV shapes in files: {shape_errors}")
+
+    if column_errors:
+        raise ValueError(f"Incorrect CSV columns in files: {column_errors}")
+
+    # Check we can load the dataset for each task
+    load_errors = []
+    for task in tasks:
+        try:
+            _ = load_dataset("../{{cookiecutter.repo_name}}", task)
+        except Exception as e:
+            load_errors.append(e)
+
+    if load_errors:
+        raise ValueError(f"Could not load predictions! Errors: {load_errors}")
+
+    typer.echo("All submission files validated! ✨ 🚀 ✨")
+    typer.echo("Now you can make a submission 🤗")
+
+
+@app.command()
+def submit(submission_name: str = typer.Option(..., prompt="Please provide a name for your submission, e.g. GPT-4 😁")):
+    subprocess.call("git pull origin main".split())
+    _update_submission_name(submission_name)
+    subprocess.call(["git", "add", "data/*predictions.csv", "README.md"])
+    subprocess.call(["git", "commit", "-m", f"Submission: {submission_name} "])
+    subprocess.call(["git", "push"])
+
+    today = datetime.date.today()
+    # MON = 0, SUN = 6 -> SUN = 0 .. SAT = 6
+    idx = (today.weekday() + 1) % 7
+    sun = today + datetime.timedelta(7 - idx)
+    typer.echo("Submission successful! 🎉 🥳 🎉")
+    typer.echo(f"Your submission will be evaulated on {sun:%A %d %B %Y} ⏳")
+
+
+if __name__ == "__main__":
+    app()

{{cookiecutter.repo_name}}/expert.py

@@ -0,0 +1,56 @@
+from packaging import version
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from torch.nn.utils.rnn import pad_sequence
+
+import fairseq
+from s3prl.upstream.interfaces import UpstreamBase
+
+
+SAMPLE_RATE = 16000
+EXAMPLE_SEC = 5
+
+class UpstreamExpert(UpstreamBase):
+    def __init__(self, ckpt, **kwargs):
+        super().__init__(**kwargs)
+        assert version.parse(fairseq.__version__) > version.parse(
+            "0.10.2"
+        ), "Please install the fairseq master branch."
+
+        model, cfg, task = fairseq.checkpoint_utils.load_model_ensemble_and_task(
+            [ckpt]
+        )
+        self.model = model[0]
+        self.task = task
+
+        if len(self.hooks) == 0:
+            module_name = "self.model.encoder.layers"
+            for module_id in range(len(eval(module_name))):
+                self.add_hook(
+                    f"{module_name}[{module_id}]",
+                    lambda input, output: input[0].transpose(0, 1),
+                )
+            self.add_hook("self.model.encoder", lambda input, output: output[0])
+
+    def forward(self, wavs):
+        if self.task.cfg.normalize:
+            wavs = [F.layer_norm(wav, wav.shape) for wav in wavs]
+
+        device = wavs[0].device
+        wav_lengths = torch.LongTensor([len(wav) for wav in wavs]).to(device)
+        wav_padding_mask = ~torch.lt(
+            torch.arange(max(wav_lengths)).unsqueeze(0).to(device),
+            wav_lengths.unsqueeze(1),
+        )
+        padded_wav = pad_sequence(wavs, batch_first=True)
+
+        features, feat_padding_mask = self.model.extract_features(
+            padded_wav,
+            padding_mask=wav_padding_mask,
+            mask=None,
+        )
+        return {
+            "default": features,
+        }

{{cookiecutter.repo_name}}/requirements.txt

@@ -0,0 +1 @@
+typer