Upload model

README.md

@@ -0,0 +1,96 @@
+---
+language: en
+datasets:
+- superb
+tags:
+- speech
+- audio
+- wav2vec2
+- audio-classification
+license: apache-2.0
+---
+
+# Wav2Vec2-Large for Keyword Spotting
+
+## Model description
+
+This is a ported version of 
+[S3PRL's Wav2Vec2 for the SUPERB Keyword Spotting task](https://github.com/s3prl/s3prl/tree/master/s3prl/downstream/speech_commands).
+
+The base model is [wav2vec2-large-lv60](https://huggingface.co/facebook/wav2vec2-large-lv60), 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
+
+Keyword Spotting (KS) detects preregistered keywords by classifying utterances into a predefined set of 
+words. The task is usually performed on-device for the fast response time. Thus, accuracy, model size, and
+inference time are all crucial. SUPERB uses the widely used 
+[Speech Commands dataset v1.0](https://www.tensorflow.org/datasets/catalog/speech_commands) for the task.
+The dataset consists of ten classes of keywords, a class for silence, and an unknown class to include the
+false positive. 
+
+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#ks-keyword-spotting).
+
+
+## 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", "ks", split="test")
+
+classifier = pipeline("audio-classification", model="superb/wav2vec2-large-superb-ks")
+labels = classifier(dataset[0]["file"], top_k=5)
+```
+
+Or use the model directly:
+```python
+import torch
+from datasets import load_dataset
+from transformers import Wav2Vec2ForSequenceClassification, Wav2Vec2FeatureExtractor
+from torchaudio.sox_effects import apply_effects_file
+
+effects = [["channels", "1"], ["rate", "16000"], ["gain", "-3.0"]]
+def map_to_array(example):
+    speech, _ = apply_effects_file(example["file"], effects)
+    example["speech"] = speech.squeeze(0).numpy()
+    return example
+
+# load a demo dataset and read audio files
+dataset = load_dataset("anton-l/superb_demo", "ks", split="test")
+dataset = dataset.map(map_to_array)
+
+model = Wav2Vec2ForSequenceClassification.from_pretrained("superb/wav2vec2-large-superb-ks")
+feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained("superb/wav2vec2-large-superb-ks")
+
+# 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** |
+|--------|-----------|------------------|
+|**test**| `0.9666`  | `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 +1,108 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-lv60",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "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,
+  "diversity_loss_weight": 0.1,
+  "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,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "yes",
+    "1": "no",
+    "2": "up",
+    "3": "down",
+    "4": "left",
+    "5": "right",
+    "6": "on",
+    "7": "off",
+    "8": "stop",
+    "9": "go",
+    "10": "_unknown_",
+    "11": "_silence_"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "_silence_": 11,
+    "_unknown_": 10,
+    "down": 3,
+    "go": 9,
+    "left": 4,
+    "no": 1,
+    "off": 7,
+    "on": 6,
+    "right": 5,
+    "stop": 8,
+    "up": 2,
+    "yes": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_prob": 0.05,
+  "model_type": "wav2vec2",
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 768,
+  "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": false,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be36f743cf72df29a247523f697f35fab379511ea935547fda6fa79ca9c9e874
+size 1262980715