init

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.

README.md

@@ -0,0 +1,182 @@
+# SUPERB Submission Template
+
+Welcome to the [SUPERB Challenge](https://superbbenchmark.org/challenge-slt2022/challenge_overview)! SUPERB is a collection of benchmarking resources to evaluate the capability of a universal shared representation for speech processing. It comes with a benchmark on the publicly available datasets and a challenge on a secret/not released hidden dataset. In SUPERB Challenge, a challenging hidden dataset is newly recorded to evaluate the ultimate generaliziblity across various tasks and data.
+
+You can participate the challenge by simply submitting your self-supervised (SSL) pretrained models (model definition & pretrained weights), and we benchmark it with the hidden datasets. This repository constains useful tools to let you easliy [submit](https://superbbenchmark.org/submit) your models ***privately*** for evaluation to [the challenge hidden-set leaderboard](https://superbbenchmark.org/leaderboard?track=constrained&subset=Hidden+Dev+Set).
+
+1. Generate a submission template
+2. Validate the format/interface correctness of your model
+3. Upload to Huggingface's Hub (privately)
+4. Submit the upload information to [SUPERB website](https://superbbenchmark.org/submit)
+
+#### Note 1.
+
+We accept pre-trained models in PyTorch by default. If you wish to submit upstreams in non-PyTorch frameworks, please mail to [[email protected]](mailto:[email protected])!
+
+#### Note 2.
+
+If you are not feasible to submit the pre-trained model, please mail to [[email protected]](mailto:[email protected]) for us to see how to help!
+
+## Quickstart
+
+### 1. Add model interfaces
+
+#### forward
+
+Extract features from waveforms.
+
+- **Input:** A list of waveforms in 16000 Hz
+
+    ```python
+    SAMPLE_RATE = 16000
+    BATCH_SIZE = 8
+    EXAMPLE_SEC = 10
+    wavs = [torch.randn(SAMPLE_RATE * EXAMPLE_SEC).cuda() for _ in range(BATCH_SIZE)]
+    ```
+
+- **Output:** A dictionary with a key "hidden_states" (for compatiblility with old ver.). The value is **a list** of padded sequences in the same shape of **(batch_size, max_sequence_length_of_batch, hidden_size)** for weighted-sum to work. It is welcome to perform some task-specified / independent pre- / post-processing on the upstream's raw hidden-sets, including upsampling and downsampling. However, all the values must come from **a single upstream model**:
+
+    ```python
+    tasks = ["hidden_states", "PR", "SID", "ER", "ASR", "ASV", "SD", "QbE", "ST", "SS", "SE", "secret"]
+    for task in tasks:
+        # you can do task-specified pre- / post-processing depend on the arg "upstream_feature_selection"
+        results = upstream(wavs, upstream_feature_selection=task)
+        hidden_states = results["hidden_states"]
+        assert isinstance(results, dict)
+        assert isinstance(hidden_states, list)
+
+        for state in hidden_states:
+            assert isinstance(state, torch.Tensor)
+            assert state.dim() == 3, "(batch_size, max_sequence_length_of_batch, hidden_size)"
+            assert state.shape == hidden_states[0].shape
+    ```
+
+#### get_downsample_rates
+
+Provide the downsample rate **from 16000 Hz waveforms** for each task's representation in the dict. For the standard 10ms stride representation, the downsample rate is 160.
+
+```python
+SAMPLE_RATE = 16000
+MSEC_PER_SEC = 1000
+downsample_rate = SAMPLE_RATE * 10 / MSEC_PER_SEC  # 160
+```
+
+The downsample rate will be used to:
+
+1. Calculate the valid representation length of each utterance in the output padded representation.
+2. Prepare the training materials according to the representation's downsample rate for frame-level tasks, e.g. SD, SE, and SS.
+
+- **Input:** the task key (str)
+- **Output:** the downsample rate (int) of the representation for that task
+
+```python
+for task in tasks:
+    assert isinstance(task, str)
+    downsample_rate = upstream.get_downsample_rate(task)
+    assert isinstance(downsample_rate, int)
+    print("The upstream's representation for {task}"
+        f" has the downsample rate of {downsample_rate}.")
+```
+
+### 2. Create an account and organization 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 new organization and invite the SUPERB Hidden Set Committee to join. You will upload your model to a repository under this organization so that members inside it can access the model which is not publicly available.
+
+* [superb-hidden-set](https://huggingface.co/superb-hidden-set)
+
+### 3. 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-submit python=3.8 && conda activate superb-submit
+# 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 packages for the submissions
+├── expert.py               <- Your model definition
+└── model.pt                <- Your model weights
+```
+
+### 4. 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://superbbenchmark.org/leaderboard?subset=Hidden+Dev+Set), there are 4 main steps:
+
+1. Modify `expert.py` and change `model.pt` so we can initialize an upstream model following the [challenge policy](https://superbbenchmark.org/challenge-slt2022/upstream) by:
+
+    ```python
+    upstream = UpstreamExpert(ckpt="./model.pt")
+    ```
+
+    ***Package Dependency:*** Note that we only install `torch` package so far by following the above steps. If your model needs more packages, you can modify the `requirement.txt` to meet your need and install them inside the current conda environment. We will install the packages you list in the `requirement.txt` before initializing the upstream model.
+
+2. Validate the upstream model's interface meets the requirements in the [challenge policy](https://superbbenchmark.org/challenge-slt2022/upstream). If everything is correct, you should see the following message: "All submission files validated! Now you can make a submission."
+
+    ```
+    python cli.py validate
+    ```
+
+3. Push the model to the Hub! If there are no errors, you should see the following message: "Upload successful!"
+
+    ```
+    python cli.py upload "commit message: my best model"
+    ```
+
+4. [Make a submission at SUPERB website](https://superbbenchmark.org/submit) by uniquely indentifying this uploaded model with the following information, which can be shown by:
+
+    ```
+    python cli.py info
+    ```
+
+    - Organization Name
+    - Repository Name
+    - Commit Hash (full 40 characters)
+
+After you finish the above 4 steps. You will see a new entry in your [SUPERB profile page](https://superbbenchmark.org/profile) (need login) which does not have any benchmark numbers yet. Please wait for us to finetuned it on the hidden dataset and get the benchmark results. The results will be revealed within one week. Please stay tuned!

cli.py

@@ -0,0 +1,78 @@
+import typer
+import torch
+import subprocess
+from pathlib import Path
+
+from expert import UpstreamExpert
+
+SUBMISSION_FILES = ["expert.py", "model.pt"]
+SAMPLE_RATE = 16000
+SECONDS = [2, 1.8, 3.7]
+
+app = typer.Typer()
+
+@app.command()
+def validate():
+    # Check that all the expected files exist
+    for file in SUBMISSION_FILES:
+        if not Path(file).is_file():
+            raise ValueError(f"File {file} not found! Please include {file} in your submission")
+
+    try:
+        upstream = UpstreamExpert(ckpt="model.pt")
+        samples = [round(SAMPLE_RATE * sec) for sec in SECONDS]
+        wavs = [torch.rand(sample) for sample in samples]
+        results = upstream(wavs)
+
+        assert isinstance(results, dict)
+        tasks = ["PR", "SID", "ER", "ASR", "ASV", "SD", "QbE", "ST", "SS", "SE", "secret"]
+        for task in tasks:
+            hidden_states = results.get(task, results["hidden_states"])
+            assert isinstance(hidden_states, list)
+
+            for state in hidden_states:
+                assert isinstance(state, torch.Tensor)
+                assert state.dim() == 3, "(batch_size, max_sequence_length_of_batch, hidden_size)"
+                assert state.shape == hidden_states[0].shape
+
+            downsample_rate = upstream.get_downsample_rates(task)
+            assert isinstance(downsample_rate, int)
+            assert abs(round(max(samples) / downsample_rate) - hidden_states[0].size(1)) < 5, "wrong downsample rate"
+
+    except:
+        print("Please check the Upstream Specification on https://superbbenchmark.org/challenge-slt2022/upstream")
+        raise
+
+    typer.echo("All submission files validated!")
+    typer.echo("Now you can upload these files to huggingface's Hub.")
+
+
+@app.command()
+def upload(commit_message: str):
+    subprocess.call("git pull origin main".split())
+    subprocess.call(["git", "add", "."])
+    subprocess.call(["git", "commit", "-m", f"Upload Upstream: {commit_message} "])
+    subprocess.call(["git", "push"])
+    typer.echo("Upload successful!")
+    typer.echo("Please go to https://superbbenchmark.org/submit to make a submission with the following information:")
+    typer.echo("1. Organization Name")
+    typer.echo("2. Repository Name")
+    typer.echo("3. Commit Hash (full 40 characters)")
+    typer.echo("These information can be shown by: python cli.py info")
+
+@app.command()
+def info():
+    result = subprocess.run(["git", "config", "--get", "remote.origin.url"], capture_output=True)
+    url = result.stdout.decode("utf-8").strip()
+    organization = url.split("/")[-2]
+    repo = url.split("/")[-1]
+
+    result = subprocess.run(["git", "rev-parse", "HEAD"], capture_output=True)
+    commit_hash = result.stdout.decode("utf-8").strip()
+
+    typer.echo(f"Organization Name: {organization}")
+    typer.echo(f"Repository Name: {repo}")
+    typer.echo(f"Commit Hash: {commit_hash}")
+
+if __name__ == "__main__":
+    app()

expert.py

@@ -0,0 +1,145 @@
+from collections import OrderedDict
+from typing import List, Union, Dict
+
+import torch
+import torch.nn as nn
+from torch import Tensor
+from torch.nn.utils.rnn import pad_sequence
+
+import fairseq
+
+# class Model(nn.Module):
+#     def __init__(self):
+#         super().__init__()
+#         # The model needs to be a nn.Module for finetuning, not required for representation extraction
+#         self.model1 = nn.Linear(1, HIDDEN_DIM)
+#         self.model2 = nn.Linear(HIDDEN_DIM, HIDDEN_DIM)
+
+#     def forward(self, wavs, upstream_feature_selection="hidden_states"):
+#         # You can do task-specified pre- / post-processing based on upstream_feature_selection
+#         hidden = self.model1(wavs)
+#         # hidden: (batch_size, max_len, hidden_dim)
+
+#         feature = self.model2(hidden)
+#         # feature: (batch_size, max_len, hidden_dim)
+
+#         return [hidden, feature]
+
+class UpstreamExpert(nn.Module):
+    def __init__(
+        self,
+        ckpt: str = "https://dl.fbaipublicfiles.com/hubert/hubert_base_ls960.pt",
+        upstream_feature_selection: str = "hidden_states",
+        **kwargs):
+        """
+        Args:
+            ckpt:
+                The checkpoint path for loading your pretrained weights.
+                Should be fixed as model.pt for SUPERB Challenge.
+            upstream_feature_selection:
+                The value could be 
+                'hidden_states', 'PR', 'SID', 'ER', 'ASR', 'QbE', 'ASV', 'SD', 'ST', 'SE', 'SS', 'secret', or others(new tasks).
+                You can use it to control which task-specified pre- / post-processing to do.
+        """
+        super().__init__()
+        self.name = "[Example UpstreamExpert]"
+        self.upstream_feature_selection = upstream_feature_selection
+
+        # # You can use ckpt to load your pretrained weights
+        # ckpt = torch.load(ckpt, map_location="cpu")
+        # self.model = Model()
+        # self.model.load_state_dict(ckpt)
+
+        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
+
+
+
+
+
+
+
+    def get_downsample_rates(self, key: str) -> int:
+        """
+        Since we do not do any downsampling in this example upstream
+        All keys' corresponding representations have downsample rate of 1
+        Eg. 10ms stride representation has the downsample rate 160 (input wavs are all in 16kHz)
+        """
+        return 320
+
+    def forward(self, wavs: List[Tensor]) -> Dict[str, List[Tensor]]:
+        """
+        When the returning Dict contains the List with more than one Tensor,
+        those Tensors should be in the same shape to train a weighted-sum on them.
+        """
+        wavs_silence = []
+
+
+        #Total 7 settings
+
+        #original
+        wavs_silence = wavs
+
+
+        #front, 5
+        for wav in wavs:
+            temp_wav = torch.zeros(len(wav)//5).to(wav.device)
+            wavs_silence.append(torch.cat((temp_wav, wav)))
+
+        #front, 10
+        for wav in wavs:
+            temp_wav = torch.zeros(len(wav)//10).to(wav.device)
+            wavs_silence.append(torch.cat((temp_wav, wav)))
+
+        #front, 20
+        for wav in wavs:
+            temp_wav = torch.zeros(len(wav)//20).to(wav.device)
+            wavs_silence.append(torch.cat((temp_wav, wav)))
+
+        #end, 5
+        for wav in wavs:
+            temp_wav = torch.zeros(len(wav)//5).to(wav.device)
+            wavs_silence.append(torch.cat((wav, temp_wav)))
+
+        #end, 10
+        for wav in wavs:
+            temp_wav = torch.zeros(len(wav)//10).to(wav.device)
+            wavs_silence.append(torch.cat((wav, temp_wav)))
+
+        #end, 20
+        for wav in wavs:
+            temp_wav = torch.zeros(len(wav)//20).to(wav.device)
+            wavs_silence.append(torch.cat((wav, temp_wav)))
+
+
+        wavs = wavs_silence
+
+        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,
+        )
+
+
+        # Deprecated! Do not do any task-specified postprocess below
+        # You can use the init arg "upstream_feature_selection" to control which task-specified pre- / post-processing to do.
+        # The "hidden_states" key will be used as default in many cases
+        # Others keys in this example are presented for SUPERB Challenge
+        return {
+            "hidden_states": features,
+        }

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:151456b83765c14f38da56dad79771cc576be7ccbe088536af558cb6761238f0
+size 1823

requirements.txt

@@ -0,0 +1,2 @@
+typer
+torch