copied w2v fb

README.md

@@ -0,0 +1,63 @@
+---
+language: nl
+datasets:
+- common_voice
+tags:
+- speech
+- audio
+- automatic-speech-recognition
+license: apache-2.0
+---
+
+## Evaluation on Common Voice NL Test
+
+```python
+import torchaudio
+from datasets import load_dataset, load_metric
+from transformers import (
+    Wav2Vec2ForCTC,
+    Wav2Vec2Processor,
+)
+import torch
+import re
+import sys
+
+model_name = "facebook/wav2vec2-large-xlsr-53-dutch"
+device = "cuda"
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"]'  # noqa: W605
+
+model = Wav2Vec2ForCTC.from_pretrained(model_name).to(device)
+processor = Wav2Vec2Processor.from_pretrained(model_name)
+
+ds = load_dataset("common_voice", "nl", split="test", data_dir="./cv-corpus-6.1-2020-12-11")
+
+resampler = torchaudio.transforms.Resample(orig_freq=48_000, new_freq=16_000)
+
+def map_to_array(batch):
+    speech, _ = torchaudio.load(batch["path"])
+    batch["speech"] = resampler.forward(speech.squeeze(0)).numpy()
+    batch["sampling_rate"] = resampler.new_freq
+    batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower().replace("’", "'")
+    return batch
+
+ds = ds.map(map_to_array)
+
+
+def map_to_pred(batch):
+    features = processor(batch["speech"], sampling_rate=batch["sampling_rate"][0], padding=True, return_tensors="pt")
+    input_values = features.input_values.to(device)
+    attention_mask = features.attention_mask.to(device)
+    with torch.no_grad():
+        logits = model(input_values, attention_mask=attention_mask).logits
+    pred_ids = torch.argmax(logits, dim=-1)
+    batch["predicted"] = processor.batch_decode(pred_ids)
+    batch["target"] = batch["sentence"]
+    return batch
+
+result = ds.map(map_to_pred, batched=True, batch_size=16, remove_columns=list(ds.features.keys()))
+
+wer = load_metric("wer")
+print(wer.compute(predictions=result["predicted"], references=result["target"]))
+```
+
+**Result**: 21.1 %

config.json

@@ -0,0 +1,68 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 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,
+  "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": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "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": 0.1,
+  "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_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "transformers_version": "4.4.0.dev0",
+  "vocab_size": 50
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9974b52afaf933d231d2ada715ff43a40a97c8d2ced1c36aafece145d6fcab8b
+size 1261975272

local_disk0/w2v-sub/.gitattributes

@@ -0,0 +1,17 @@
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tar.gz filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text

preprocessor_config.json

@@ -0,0 +1,8 @@
+{
+  "do_normalize": true,
+  "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:c803055f87112ce0b28b3169f6c0960a792ba43c301cb6b9eea8de2179e2d8b0
+size 1262132951

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": true, "word_delimiter_token": "|", "special_tokens_map_file": "/home/patrick/hugging_face/add_wav2vec/hf/wav2vec2-large-xlsr-53-dutch/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/home/patrick/hugging_face/add_wav2vec/hf/wav2vec2-large-xlsr-53-dutch"}

vocab.json

@@ -0,0 +1 @@
+{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "E": 4, "N": 5, "A": 6, "I": 7, "T": 8, "O": 9, "D": 10, "R": 11, "|": 12, "L": 13, "S": 14, "H": 15, "G": 16, "M": 17, "K": 18, "V": 19, "J": 20, "W": 21, "Z": 22, "U": 23, "B": 24, "C": 25, "P": 26, "F": 27, "Y": 28, "É": 29, "'": 30, "X": 31, "Ë": 32, "Q": 33, "-": 34, "Ê": 35, "À": 36, "Ä": 37, "È": 38, "Ï": 39, "Â": 40, "Û": 41, "Ö": 42, "Ô": 43, "Ü": 44, "Î": 45, "Ç": 46, "Æ": 47, "Ù": 48, "Œ": 49}