Upload model

README.md

@@ -0,0 +1,93 @@
+---
+language: en
+datasets:
+- superb
+tags:
+- speech
+- audio
+- hubert
+- audio-classification
+license: apache-2.0
+---
+
+# Hubert-Large for Emotion Recognition
+
+## Model description
+
+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 [hubert-large-ll60k](https://huggingface.co/facebook/hubert-large-ll60k), which is pretrained on 16kHz 
+sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz. 
+
+For more information refer to [SUPERB: Speech processing Universal PERformance Benchmark](https://arxiv.org/abs/2105.01051)
+
+## Task and dataset description
+
+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.
+
+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 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-large-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-large-superb-er")
+feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained("superb/hubert-large-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**| `0.6762`  | `N/A`         |
+
+### 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}
+}
+```

config.json

@@ -0,0 +1,91 @@
+{
+  "_name_or_path": "facebook/hubert-large-ll60k",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.1,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "neu",
+    "1": "hap",
+    "2": "ang",
+    "3": "sad"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "ang": 2,
+    "hap": 1,
+    "neu": 0,
+    "sad": 3
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.075,
+  "mask_time_selection": "static",
+  "model_type": "hubert",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.0.dev0",
+  "use_weighted_layer_sum": true,
+  "vocab_size": 32
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9e5f9386285300a3e5e7d7f6852f578fec7bb0cc75e89661a3f98db7112237d
+size 1262970923