add all files

README.md

@@ -0,0 +1,109 @@
+---
+language: en
+datasets:
+- librispeech_asr
+tags:
+- speech
+- audio
+- automatic-speech-recognition
+- hf-asr-leaderboard
+license: apache-2.0
+model-index:
+- name: wav2vec2-conformer-rel-pos-large-960h-ft
+  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: 1.96
+---
+
+# Wav2Vec2-Conformer-Large-960h with Rotary Position Embeddings
+
+[Facebook's Wav2Vec2 Conformer (TODO-add link)]()
+
+Wav2Vec2 Conformer with rotary position embeddings, pretrained and fine-tuned on 960 hours of Librispeech on 16kHz sampled speech audio. When using the model make sure that your speech input is also sampled at 16Khz.
+
+[Paper (TODO)](https://arxiv.org/abs/2006.11477)
+
+Authors: ...
+
+**Abstract**
+
+...
+
+The original model can be found under https://github.com/pytorch/fairseq/tree/master/examples/wav2vec#wav2vec-20.
+
+
+# Usage
+
+To transcribe audio files the model can be used as a standalone acoustic model as follows:
+
+```python
+ from transformers import Wav2Vec2Processor, Wav2Vec2ConformerForCTC
+ from datasets import load_dataset
+ import torch
+ 
+ # load model and processor
+ processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-conformer-rope-large-960h-ft")
+ model = Wav2Vec2ConformerForCTC.from_pretrained("facebook/wav2vec2-conformer-rope-large-960h-ft")
+     
+ # load dummy dataset and read soundfiles
+ ds = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
+ 
+ # tokenize
+ input_values = processor(ds[0]["audio"]["array"], return_tensors="pt", padding="longest").input_values
+ 
+ # retrieve logits
+ logits = model(input_values).logits
+ 
+ # take argmax and decode
+ predicted_ids = torch.argmax(logits, dim=-1)
+ transcription = processor.batch_decode(predicted_ids)
+ ```
+ 
+  ## Evaluation
+ 
+ This code snippet shows how to evaluate **facebook/wav2vec2-conformer-rope-large-960h-ft** on LibriSpeech's "clean" and "other" test data.
+ 
+```python
+from datasets import load_dataset
+from transformers import Wav2Vec2ConformerForCTC, Wav2Vec2Processor
+import torch
+from jiwer import wer
+
+
+librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
+
+model = Wav2Vec2ConformerForCTC.from_pretrained("facebook/wav2vec2-conformer-rope-large-960h-ft").to("cuda")
+processor = Wav2Vec2Processor.from_pretrained("facebook/wav2vec2-conformer-rope-large-960h-ft")
+
+def map_to_pred(batch):
+    inputs = processor(batch["audio"]["array"], return_tensors="pt", padding="longest")
+    input_values = inputs.input_values.to("cuda")
+    attention_mask = inputs.attention_mask.to("cuda")
+    
+    with torch.no_grad():
+        logits = model(input_values, attention_mask=attention_mask).logits
+
+    predicted_ids = torch.argmax(logits, dim=-1)
+    transcription = processor.batch_decode(predicted_ids)
+    batch["transcription"] = transcription
+    return batch
+
+result = librispeech_eval.map(map_to_pred, remove_columns=["audio"])
+
+print("WER:", wer(result["text"], result["transcription"]))
+```
+
+*Result (WER)*:
+
+| "clean" | "other" |
+|---|---|
+| 1.96 | 3.98 |

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 +1,113 @@
+{
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ConformerForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_depthwise_kernel_size": 31,
+  "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": "swish",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 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_prob": 0.05,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-conformer",
+  "num_adapter_layers": 3,
+  "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,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "position_embeddings_type": "rotary",
+  "proj_codevector_dim": 768,
+  "rotary_embedding_base": 10000,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

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,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:665a23a077e25751f27d2580b7d3d222d00de5954b752b8661974f33dc005053
+size 2373994447

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": " ", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2Processor"}

vocab.json

@@ -0,0 +1 @@
+{"<s>": 1, "<pad>": 0, "</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}