first commit

README.md

@@ -0,0 +1,126 @@
+---
+language: eu
+datasets:
+- common_voice 
+metrics:
+- wer
+tags:
+- audio
+- automatic-speech-recognition
+- speech
+- xlsr-fine-tuning-week
+license: apache-2.0
+model-index:
+- name: XLSR Wav2Vec2 Basque by Cahya
+  results:
+  - task: 
+      name: Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice eu
+      type: common_voice
+      args: eu
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 14.68
+---
+
+# Wav2Vec2-Large-XLSR-Basque
+
+This is the model for Wav2Vec2-Large-XLSR-Basque, a fine-tuned 
+[facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53)
+model on the [Basque Common Voice dataset](https://huggingface.co/datasets/common_voice).
+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", "eu", split="test[:2%]")
+
+processor = Wav2Vec2Processor.from_pretrained("cahya-wirawan/wav2vec2-large-xlsr-basque")
+model = Wav2Vec2ForCTC.from_pretrained("cahya-wirawan/wav2vec2-large-xlsr-basque")
+
+
+# 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"])
+  resampler = torchaudio.transforms.Resample(sampling_rate, 16_000)
+  batch["speech"] = resampler(speech_array).squeeze().numpy()
+  return batch
+
+test_dataset = test_dataset.map(speech_file_to_array_fn)
+inputs = processor(test_dataset[:2]["speech"], 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[:2]["sentence"])
+```
+
+
+## Evaluation
+
+The model can be evaluated as follows on the Basque test data of Common Voice.
+
+```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", "eu", split="test")
+wer = load_metric("wer")
+
+processor = Wav2Vec2Processor.from_pretrained("cahya-wirawan/wav2vec2-large-xlsr-basque")
+model = Wav2Vec2ForCTC.from_pretrained("cahya-wirawan/wav2vec2-large-xlsr-basque") 
+model.to("cuda")
+
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“\%\‘\'\”\�]'
+
+
+# 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"])
+  resampler = torchaudio.transforms.Resample(sampling_rate, 16_000)
+  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**: 14.68 %
+
+## Training
+
+The Common Voice `train`, `validation`, and ... datasets were used for training as well as ... and ...  # TODO
+
+The script used for training can be found [here](https://github.com/cahya-wirawan/indonesian-speech-recognition) 

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.055,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.094,
+  "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": true,
+  "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": 0.04,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.047,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.041,
+  "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": 0.4,
+  "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": 30,
+  "transformers_version": "4.5.0.dev0",
+  "vocab_size": 31
+}

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 sha256:2e0e448f2fea8a4379b4ed27cd56e5ff77b1bd281db12b5a7bccd0d80f415fec
+size 1262060951

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