Upload 8 files

README.md

@@ -0,0 +1,129 @@
+# Wav2Vec2-Large-XLSR-53
+
+---
+language: gl
+datasets:
+- OpenSLR 77
+metrics:
+- wer
+tags:
+- audio
+- automatic-speech-recognition
+- speech
+- xlsr-fine-tuning-week
+license: apache-2.0
+model-index:
+- name: Galician Wav2Vec2-Large-XLSR-53
+  results:
+  - task: 
+      name: Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: OpenSLR
+      type: openslr
+      args: gl
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 16.79
+---
+
+Wav2Vec2-Large-XLSR-53-galician
+
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on galician using the [OpenSLR](https://huggingface.co/datasets/common_voice) dataset
+
+When using this model, make sure that your speech input is sampled at 16kHz.
+
+## Usage
+
+The model can be used directly (without a language model) as follows:
+
+```python
+import torch
+import torchaudio
+from datasets import load_dataset
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+
+test_dataset = load_dataset("common_voice", "gl", split="test[:2%]")  # This is not available yet, load OpenSLR or your dataset instead
+
+processor = Wav2Vec2Processor.from_pretrained("diego-fustes/wav2vec2-large-xlsr-gl")
+model = Wav2Vec2ForCTC.from_pretrained("diego-fustes/wav2vec2-large-xlsr-gl")
+
+resampler = torchaudio.transforms.Resample(48_000, 16_000)
+
+# Preprocessing the datasets.
+# We need to read the aduio files as arrays
+def speech_file_to_array_fn(batch):
+   speech_array, sampling_rate = torchaudio.load(batch["path"])
+   batch["speech"] = resampler(speech_array).squeeze().numpy()
+   return batch
+
+test_dataset = test_dataset.map(speech_file_to_array_fn)
+inputs = processor(test_dataset["speech"][:2], sampling_rate=16_000, return_tensors="pt", padding=True)
+
+with torch.no_grad():
+  logits = model(inputs.input_values, attention_mask=inputs.attention_mask).logits
+
+predicted_ids = torch.argmax(logits, dim=-1)
+
+print("Prediction:", processor.batch_decode(predicted_ids))
+print("Reference:", test_dataset["sentence"][:2])
+```
+
+
+## Evaluation
+
+The model can be evaluated as follows on the Galician test data of Common Voice (when it is released).
+
+```python
+import torch
+import torchaudio
+from datasets import load_dataset, load_metric
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+import re
+
+test_dataset = load_dataset("common_voice", "gl", split="test")   # This is not available yet, load OpenSLR or your dataset instead
+wer = load_metric("wer")
+
+processor = Wav2Vec2Processor.from_pretrained("diego-fustes/wav2vec2-large-xlsr-gl")
+model = Wav2Vec2ForCTC.from_pretrained("diego-fustes/wav2vec2-large-xlsr-gl")
+model.to("cuda")
+
+chars_to_ignore_regex = '[^a-záéíóúñ ]'
+resampler = torchaudio.transforms.Resample(48_000, 16_000)
+
+# Preprocessing the datasets.
+# We need to read the aduio files as arrays
+def speech_file_to_array_fn(batch):
+  batch["sentence"] = re.sub(chars_to_ignore_regex, '', batch["sentence"]).lower()
+  speech_array, sampling_rate = torchaudio.load(batch["path"])
+  batch["speech"] = resampler(speech_array).squeeze().numpy()
+  return batch
+
+test_dataset = test_dataset.map(speech_file_to_array_fn)
+
+# Preprocessing the datasets.
+# We need to read the aduio files as arrays
+def evaluate(batch):
+  inputs = processor(batch["speech"], sampling_rate=16_000, return_tensors="pt", padding=True)
+
+  with torch.no_grad():
+    logits = model(inputs.input_values.to("cuda"), attention_mask=inputs.attention_mask.to("cuda")).logits
+  
+  pred_ids = torch.argmax(logits, dim=-1)
+  batch["pred_strings"] = processor.batch_decode(pred_ids)
+  return batch
+
+result = test_dataset.map(evaluate, batched=True, batch_size=8)
+
+print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
+```
+
+**Test Result**: 16.79 % on OpenSLR split
+
+
+## Training
+
+The OpenSLR [SLR77](https://openslr.org/77/) dataset was used for training and validation. The dataset was split as 70% for training, 15% for validation and 15% for testing  
+
+The script used for training can be found [here](https://github.com/diego-fustes/xlsr-fine-tuning-gl)

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "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": "mean",
+  "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": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "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": 34,
+  "transformers_version": "4.4.0",
+  "vocab_size": 35
+}

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec57f94db39e61e6c7ebf0f4418534b5366e9b8ac9bb2c3f35a4d002bd0e44ec
+size 65536

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 sha256:70025d6fea750e66074d0d34c55a1ab880a80ed304d6ce7750d8bfb58840f69e
+size 65536

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": "|"}

vocab.json

@@ -0,0 +1 @@
+{"g": 0, "m": 1, "n": 2, "y": 3, "x": 4, "s": 5, "e": 6, "á": 7, "ó": 9, "w": 10, "í": 11, "i": 12, "ñ": 13, "q": 14, "c": 15, "j": 16, "h": 17, "p": 18, "l": 19, "u": 20, "d": 21, "é": 22, "z": 23, "o": 24, "ú": 25, "r": 26, "b": 27, "f": 28, "k": 29, "v": 30, "t": 31, "a": 32, "|": 8, "[UNK]": 33, "[PAD]": 34}