upload all files

README.md

@@ -0,0 +1,96 @@
+# Wav2Vec2 Acoustic Model fine-tuned on LibriSpeech
+
+Original model can be found under https://github.com/pytorch/fairseq/tree/master/examples/wav2vec#wav2vec-20.
+
+Paper: https://arxiv.org/abs/2006.11477
+
+## Usage
+
+Make sure you are working on [this branch](https://github.com/huggingface/transformers/tree/add_wav2vec) (which will be merged to master soon hopefully) of transformers:
+
+```bash
+$ git checkout add_wav2vec
+```
+
+In the following, we'll show a simple example of how the model can be used for automatic speech recognition.
+
+First, let's load the model
+
+```python
+from transformers import AutoModelForMaskedLM
+
+model = AutoModelForMaskedLM.from_pretrained("patrickvonplaten/wav2vec2-base-960h")
+
+```
+
+Next, let's load a dummy librispeech dataset
+
+```python
+from datasets import load_dataset
+import soundfile as sf
+
+libri_speech_dummy = load_dataset("patrickvonplaten/librispeech_asr_dummy", "clean", split="validation")
+
+def map_to_array(batch):
+    speech_array, _ = sf.read(batch["file"])
+    batch["speech"] = speech_array
+    return batch
+
+libri_speech_dummy = libri_speech_dummy.map(map_to_array, remove_columns=["file"])
+
+# check out dataset
+print(libri_speech_dummy)
+
+input_speech_16kHz = libri_speech_dummy[2]["speech"]
+expected_trans = libri_speech_dummy[2]["text"]
+```
+
+Cool, now we can run an inference pass to retrieve the logits:
+
+```python
+import torch
+logits = model(torch.tensor(input_speech_16kHz)[None, :])
+
+# use highest probability logits
+pred_ids = torch.argmax(logits[0], axis=-1)
+```
+
+Finally, let's decode the prediction. 
+Let's create a simple CTC-Decoder:
+
+```python
+  import numpy as np
+  from itertools import groupby
+
+  class Decoder:
+      def __init__(self, json_dict):
+          self.dict = json_dict
+          self.look_up = np.asarray(list(self.dict.keys()))
+  
+      def decode(self, ids):
+          converted_tokens = self.look_up[ids]
+          fused_tokens = [tok[0] for tok in groupby(converted_tokens)]
+          output = ' '.join(''.join(''.join(fused_tokens).split("<s>")).split("|"))
+          return output
+```
+
+and instantiate with the corresponding dict.
+
+```python
+# hard-coded json dict taken from: https://dl.fbaipublicfiles.com/fairseq/wav2vec/dict.ltr.txt
+json_dict = {"<s>": 0, "<pad>": 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}
+
+decoder = Decoder(json_dict=json_dict)
+```
+
+and decode the result
+
+```python   
+pred_trans = decoder.decode(pred_ids)
+   
+print("Prediction:\n", pred_trans)
+print("\n" + 50 * "=" + "\n")
+print("Correct result:\n", expected_trans)
+```
+
+🎉

config.json

@@ -0,0 +1,51 @@
+{
+  "architectures": [
+    "Wav2Vec2ForMaskedLM"
+  ],
+  "conv_bias": false,
+  "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
+  ],
+  "do_stable_layer_norm": false,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "model_type": "wav2vec2",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "transformers_version": "4.3.0.dev0",
+  "vocab_size": 32
+}

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}

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}