Hguimaraes
/

rd_hubert

@@ -1,199 +1,94 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
+license: cc-by-sa-4.0
+pipeline_tag: feature-extraction
+tags:
+- speech
+- automatic-speech-recognition
 library_name: transformers
+language:
+- en
 ---
+# RobustDistiller: Compressing Universal Speech Representations for Enhanced Environment Robustness
+> Self-supervised speech pre-training enables deep neural network models to capture meaningful and disentangled factors from raw waveform signals. The learned universal speech representations can then be used across numerous downstream tasks. These representations, however, are sensitive to distribution shifts caused by environmental factors, such as noise and/or room reverberation. Their large sizes, in turn, make them unfeasible for edge applications. In this work, we propose a knowledge distillation methodology termed RobustDistiller which compresses universal representations while making them more robust against environmental artifacts via a multi-task learning objective. The proposed layer-wise distillation recipe is evaluated on top of three well-established universal representations, as well as with three downstream tasks. Experimental results show the proposed methodology applied on top of the WavLM Base+ teacher model outperforming all other benchmarks across noise types and levels, as well as reverberation times. Oftentimes, the obtained results with the student model (24M parameters) achieved results inline with those of the teacher model (95M).
+**tl;dr**: Robust distillation recipe for self-supervised speech representation learning (S3RL) models that tackle jointly model compression and robustness against environmental artifacts (noise and reverberation).
+---
+## Versions
+RobustDistiller was originally proposed on our ICASSP paper, which can be found in this [**link**](https://arxiv.org/abs/2302.09437). RobustDistiller is a framework on top of common distillation recipe (e.g., DistilHuBERT).
+An extension of this work was made available at [Arxiv](https://arxiv.org/abs/2403.08654), where we further expand the work to 12 downstream tasks. In addition, we apply the RobustDistiller on top of the DPHuBERT recipe.
+---
+## Checkpoints
+| Model      | Parameters | #Layers | Teacher | Checkpoint                                        |
+| ---------- | ---------- | ---- | ----- | ------------------------------------------------- |
+| RD (WavLM) | 27M        | 2    | WavLM | [link](https://huggingface.co/Hguimaraes/rd_wavlm) |
+| RD (HuBERT)  | 27M        | 2    | HuBERT | [link](https://huggingface.co/Hguimaraes/rd_hubert)  |
+| RD (Robust HuBERT) | 27M       | 2    | Robust HuBERT | [link](https://huggingface.co/Hguimaraes/rd_rhubert) |
+| RD (DPWavLM) | 27M       | 12 | WavLM |[link](https://huggingface.co/Hguimaraes/rd_dpwavlm) |
+---
+## 🚀 How To Use
+**Installation**
+```
+pip install -U transformers
+```
+**Load Model and Extract Features**
+```python
+import torch
+import torchaudio
+from transformers import AutoModel
+# Load pre-trained model
+model = AutoModel.from_pretrained("Hguimaraes/rd_wavlm", trust_remote_code=True).cuda().eval()
+# Load audio and resample to 16kHz
+wav, sr = torchaudio.load_audio("path/to/audio")  # (batch_size, wav_len)
+wav = torchaudio.functional.resample(wav, sr, 16000)
+# Extract features
+with torch.no_grad():
+    output = model(wav)
+# output["last_hidden_states"]: final output (batch_size, seq_len, encoder_dim)
+# output["hidden_states"]:      list of elements with (batch_size, seq_len, encoder_dim) tensors (features for each layer or projections)
+```
+---
+## 📖 Citation
+```bibtex
+@inproceedings{guimaraes2023robustdistiller,
+  title={RobustDistiller: Compressing Universal Speech Representations for Enhanced Environment Robustness},
+  author={Guimarães, Heitor R and Pimentel, Arthur and Avila, Anderson R and Rezagholizadeh, Mehdi and Chen, Boxing and Falk, Tiago H},
+  booktitle={ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  pages={1--5},
+  year={2023},
+  organization={IEEE}
+}
+@article{guimaraes2024efficient,
+  title={An Efficient End-to-End Approach to Noise Invariant Speech Features via Multi-Task Learning},
+  author={Guimar{\~a}es, Heitor R and Pimentel, Arthur and Avila, Anderson R and Rezagholizadeh, Mehdi and Chen, Boxing and Falk, Tiago H},
+  journal={arXiv preprint arXiv:2403.08654},
+  year={2024}
+}
+```
+---
+## Acknowledgement
+Much of our code base is based on the following repositories:
+- [S3RL](https://github.com/s3prl/s3prl)
+- [DPHuBERT](https://github.com/pyf98/DPHuBERT)
+Thank you so much to the authors!