Update info

README.md

@@ -4,27 +4,90 @@ datasets:
 - superb
 tags:
 - speech
+- audio
 - hubert
-- s3prl
+- audio-classification
 license: apache-2.0
 ---
 
 # Hubert-Base for Emotion Recognition
 
-[S3PRL speech toolkit](https://github.com/s3prl/s3prl)
+## Model description
 
-[Facebook's Hubert](https://ai.facebook.com/blog/hubert-self-supervised-representation-learning-for-speech-recognition-generation-and-compression)
+This is a ported version of 
+[S3PRL's Hubert for the SUPERB Emotion Recognition task](https://github.com/s3prl/s3prl/tree/master/s3prl/downstream/emotion).
 
-The base model is pretrained on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. 
-The classification head is trained using the Emotion Recognition part of the SUPERB dataset.
+The base model is [hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960), which is pretrained on 16kHz 
+sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. 
 
-[Paper](https://arxiv.org/abs/2105.01051)
+For more information refer to [SUPERB: Speech processing Universal PERformance Benchmark](https://arxiv.org/abs/2105.01051)
 
-Authors: Shu-wen Yang, Po-Han Chi, Yung-Sung Chuang, Cheng-I Jeff Lai, Kushal Lakhotia, Yist Y. Lin, Andy T. Liu, Jiatong Shi, Xuankai Chang, Guan-Ting Lin, Tzu-Hsien Huang, Wei-Cheng Tseng, Ko-tik Lee, Da-Rong Liu, Zili Huang, Shuyan Dong, Shang-Wen Li, Shinji Watanabe, Abdelrahman Mohamed, Hung-yi Lee
+## Task and dataset description
 
-**Abstract**
-Self-supervised learning (SSL) has proven vital for advancing research in natural language processing (NLP) and computer vision (CV). The paradigm pretrains a shared model on large volumes of unlabeled data and achieves state-of-the-art (SOTA) for various tasks with minimal adaptation. However, the speech processing community lacks a similar setup to systematically explore the paradigm. To bridge this gap, we introduce Speech processing Universal PERformance Benchmark (SUPERB). SUPERB is a leaderboard to benchmark the performance of a shared model across a wide range of speech processing tasks with minimal architecture changes and labeled data. Among multiple usages of the shared model, we especially focus on extracting the representation learned from SSL due to its preferable re-usability. We present a simple framework to solve SUPERB tasks by learning task-specialized lightweight prediction heads on top of the frozen shared model. Our results demonstrate that the framework is promising as SSL representations show competitive generalizability and accessibility across SUPERB tasks. We release SUPERB as a challenge with a leaderboard and a benchmark toolkit to fuel the research in representation learning and general speech processing.
+Emotion Recognition (ER) predicts an emotion class for each utterance. The most widely used ER dataset
+[IEMOCAP](https://sail.usc.edu/iemocap/) is adopted, and we follow the conventional evaluation protocol: 
+we drop the unbalanced emotion classes to leave the final four classes with a similar amount of data points and 
+cross-validate on five folds of the standard splits.
 
-The original model can be found under https://github.com/s3prl/s3prl/tree/master/s3prl/downstream/emotion
+For the original model's training and evaluation instructions refer to the 
+[S3PRL downstream task README](https://github.com/s3prl/s3prl/tree/master/s3prl/downstream#er-emotion-recognition).
 
-# Usage
+
+## Usage examples
+
+You can use the model via the Audio Classification pipeline:
+```python
+from datasets import load_dataset
+from transformers import pipeline
+
+dataset = load_dataset("anton-l/superb_demo", "er", split="session1")
+
+classifier = pipeline("audio-classification", model="superb/hubert-base-superb-er")
+labels = classifier(dataset[0]["file"], top_k=5)
+```
+
+Or use the model directly:
+```python
+import torch
+import librosa
+from datasets import load_dataset
+from transformers import HubertForSequenceClassification, Wav2Vec2FeatureExtractor
+
+def map_to_array(example):
+    speech, _ = librosa.load(example["file"], sr=16000, mono=True)
+    example["speech"] = speech
+    return example
+
+# load a demo dataset and read audio files
+dataset = load_dataset("anton-l/superb_demo", "er", split="session1")
+dataset = dataset.map(map_to_array)
+
+model = HubertForSequenceClassification.from_pretrained("superb/hubert-base-superb-er")
+feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained("superb/hubert-base-superb-er")
+
+# compute attention masks and normalize the waveform if needed
+inputs = feature_extractor(dataset[:4]["speech"], sampling_rate=16000, padding=True, return_tensors="pt")
+
+logits = model(**inputs).logits
+predicted_ids = torch.argmax(logits, dim=-1)
+labels = [model.config.id2label[_id] for _id in predicted_ids.tolist()]
+```
+
+## Eval results
+
+The evaluation metric is accuracy.
+
+|        | **s3prl** | **transformers** |
+|--------|-----------|------------------|
+|**session1**| `0.6492`  | `0.6359`         |
+
+### BibTeX entry and citation info
+
+```bibtex
+@article{yang2021superb,
+  title={SUPERB: Speech processing Universal PERformance Benchmark},
+  author={Yang, Shu-wen and Chi, Po-Han and Chuang, Yung-Sung and Lai, Cheng-I Jeff and Lakhotia, Kushal and Lin, Yist Y and Liu, Andy T and Shi, Jiatong and Chang, Xuankai and Lin, Guan-Ting and others},
+  journal={arXiv preprint arXiv:2105.01051},
+  year={2021}
+}
+```