up

README.md

@@ -0,0 +1,74 @@
+---
+language: en
+datasets:
+- librispeech_asr
+tags:
+- audio
+- automatic-speech-recognition
+- hf-asr-leaderboard
+license: apache-2.0
+widget:
+- example_title: Librispeech sample 1
+  src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
+- example_title: Librispeech sample 2
+  src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
+model-index:
+- name: patrickvonplaten/wav2vec2-large-960h-lv60-self-4-gram
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Librispeech (clean)
+      type: librispeech_asr
+      args: en
+    metrics:
+    - name: Test WER
+      type: wer
+      value: 1.84
+---
+
+# Wav2Vec2-Base-960h + 4-gram
+
+This model is identical to [Facebook's Wav2Vec2-Large-960h-lv60-self](https://huggingface.co/facebook/wav2vec2-large-960h-lv60-self), but is 
+augmented with an English 4-gram. The `4-gram.arpa.gz` of [Librispeech's official ngrams](https://www.openslr.org/11) is used.
+ 
+ ## Evaluation
+ 
+ This code snippet shows how to evaluate **patrickvonplaten/wav2vec2-large-960h-lv60-self-4-gram** on LibriSpeech's "clean" and "other" test data.
+ 
+```python
+from datasets import load_dataset
+from transformers import AutoModelForCTC, AutoProcessor
+import torch
+from jiwer import wer
+
+model_id = "patrickvonplaten/wav2vec2-large-960h-lv60-self-4-gram"
+
+librispeech_eval = load_dataset("librispeech_asr", "other", split="test")
+
+model = AutoModelForCTC.from_pretrained(model_id).to("cuda")
+processor = AutoProcessor.from_pretrained(model_id)
+
+def map_to_pred(batch):
+    inputs = processor(batch["audio"]["array"], sampling_rate=16_000, return_tensors="pt")
+
+    inputs = {k: v.to("cuda") for k,v in inputs.items()}
+
+    with torch.no_grad():
+        logits = model(**inputs).logits
+
+    transcription = processor.batch_decode(logits.cpu().numpy()).text[0]
+    batch["transcription"] = transcription
+    return batch
+
+result = librispeech_eval.map(map_to_pred, remove_columns=["audio"])
+
+print(wer(result["text"], result["transcription"]))
+```
+
+*Result (WER)*:
+
+| "clean" | "other" |
+|---|---|
+| 1.84 | 3.71 |

alphabet.json

@@ -0,0 +1 @@
+{"labels": ["", "<s>", "</s>", "\u2047", " ", "E", "T", "A", "O", "N", "I", "H", "S", "R", "D", "L", "U", "M", "W", "C", "F", "G", "Y", "P", "B", "V", "K", "'", "X", "J", "Q", "Z"], "is_bpe": false}

config.json

@@ -0,0 +1,80 @@
+{
+  "_name_or_path": "facebook/hubert-xlarge-ls960-ft",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertForCTC"
+  ],
+  "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,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "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_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.075,
+  "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": 48,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

language_model/4-gram.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e674d4a61df15bef37cd49183dc4fb087aaa3d7819d0ff8347068a880f033c61
+size 3124591979

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16dfe0b4aa7dc3c0e1bce84ec1505a3fecd1aefa600440a5c355b43d4b4dea1b
+size 3850416049

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": "/home/patrick_huggingface_co/.cache/huggingface/transformers/0dd9f421c5b57d7bce23fb1d1c182fd28779f145cd3b2dada47f3d2e2ecff47b.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd", "name_or_path": "facebook/hubert-xlarge-ls960-ft", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "E": 5, "T": 6, "A": 7, "O": 8, "N": 9, "I": 10, "H": 11, "S": 12, "R": 13, "D": 14, "L": 15, "U": 16, "M": 17, "W": 18, "C": 19, "F": 20, "G": 21, "Y": 22, "P": 23, "B": 24, "V": 25, "K": 26, "'": 27, "X": 28, "J": 29, "Q": 30, "Z": 31}