first commit

README.md

@@ -0,0 +1,153 @@
+---
+language: es
+datasets:
+- common_voice
+metrics:
+- wer
+- cer
+tags:
+- audio
+- automatic-speech-recognition
+- speech
+- xlsr-fine-tuning-week
+license: apache-2.0
+model-index:
+- name: XLSR Wav2Vec2 Spanish by Jonatas Grosman
+  results:
+  - task: 
+      name: Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice es
+      type: common_voice
+      args: es
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 10.07
+       - name: Test CER
+         type: cer
+         value: 3.04
+---
+
+# Wav2Vec2-Large-XLSR-53-Spanish
+
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Spanish using the [Common Voice](https://huggingface.co/datasets/common_voice).
+When using this model, make sure that your speech input is sampled at 16kHz.
+
+The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint
+
+## Usage
+
+The model can be used directly (without a language model) as follows:
+
+```python
+import torch
+import librosa
+from datasets import load_dataset
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+
+LANG_ID = "es"
+MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-spanish"
+SAMPLES = 5
+
+test_dataset = load_dataset("common_voice", LANG_ID, split=f"test[:{SAMPLES}]")
+
+processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
+model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
+
+# Preprocessing the datasets.
+# We need to read the audio files as arrays
+def speech_file_to_array_fn(batch):
+    speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
+    batch["speech"] = speech_array
+    batch["sentence"] = batch["sentence"].upper()
+    return batch
+
+test_dataset = test_dataset.map(speech_file_to_array_fn)
+inputs = processor(test_dataset["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)
+predicted_sentences = processor.batch_decode(predicted_ids)
+
+for i, predicted_sentence in enumerate(predicted_sentences):
+    print("-" * 100)
+    print("Reference:", test_dataset[i]["sentence"])
+    print("Prediction:", predicted_sentence)
+```
+
+| Reference  | Prediction |
+| ------------- | ------------- |
+| HABITA EN AGUAS POCO PROFUNDAS Y ROCOSAS. | HABITAN AGUAS POCO PROFUNDAS Y ROCOSAS |
+| OPERA PRINCIPALMENTE VUELOS DE CABOTAJE Y REGIONALES DE CARGA. | OPERA PRINCIPALMENTE VUELO DE CARBOTAJES Y REGIONALES DE CARGAN |
+| PARA VISITAR CONTACTAR PRIMERO CON LA DIRECCIÓN. | PARA VISITAR CONTACTAR PRIMERO CON LA DIRECCIÓN |
+| TRES | TRES |
+| REALIZÓ LOS ESTUDIOS PRIMARIOS EN FRANCIA, PARA CONTINUAR LUEGO EN ESPAÑA. | REALIZÓ LOS ESTUDIOS PRIMARIOS EN FRANCIA PARA CONTINUAR LUEGO EN ESPAÑA |
+
+## Evaluation
+
+The model can be evaluated as follows on the Spanish test data of Common Voice.
+
+```python
+import torch
+import re
+import librosa
+from datasets import load_dataset, load_metric
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+
+LANG_ID = "es"
+MODEL_ID = "jonatasgrosman/wav2vec2-large-xlsr-53-spanish"
+DEVICE = "cuda"
+
+CHARS_TO_IGNORE = [",", "?", "¿", ".", "!", "¡", ";", ":", '""', "%", '"', "�", "ʿ", "·", "჻", "~", "՞", 
+                   "؟", "،", "।", "॥", "«", "»", "„", "“", "”", "「", "」", "‘", "’", "《", "》", "(", ")", "[", "]",
+                   "=", "`", "_", "+", "<", ">", "…", "–", "°", "´", "ʾ", "‹", "›", "©", "®", "—", "→", "。"]
+
+test_dataset = load_dataset("common_voice", LANG_ID, split="test")
+
+wer = load_metric("wer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/wer.py
+cer = load_metric("cer.py") # https://github.com/jonatasgrosman/wav2vec2-sprint/blob/main/cer.py
+
+chars_to_ignore_regex = f"[{re.escape(''.join(CHARS_TO_IGNORE))}]"
+
+processor = Wav2Vec2Processor.from_pretrained(MODEL_ID)
+model = Wav2Vec2ForCTC.from_pretrained(MODEL_ID)
+model.to(DEVICE)
+
+# Preprocessing the datasets.
+# We need to read the audio files as arrays
+def speech_file_to_array_fn(batch):
+    with warnings.catch_warnings():
+        warnings.simplefilter("ignore")
+        speech_array, sampling_rate = librosa.load(batch["path"], sr=16_000)
+    batch["speech"] = speech_array
+    batch["sentence"] = re.sub(chars_to_ignore_regex, "", batch["sentence"]).upper()
+    return batch
+
+test_dataset = test_dataset.map(speech_file_to_array_fn)
+
+# Preprocessing the datasets.
+# We need to read the audio 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(DEVICE), attention_mask=inputs.attention_mask.to(DEVICE)).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"], chunk_size=1000)))
+print("CER: {:2f}".format(100 * cer.compute(predictions=result["pred_strings"], references=result["sentence"], chunk_size=1000)))
+```
+
+**Test Result**:
+
+- WER: 10.07%
+- CER: 3.04%

config.json

@@ -0,0 +1,69 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.05,
+  "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": 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": 0.05,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.05,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "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": "4.5.0.dev0",
+  "vocab_size": 40
+}

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 sha256:60c878351b0f005d0575b84427412dc7500ab0090e5513dd1e3b4343cb87aa4e
+size 1262097815

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

vocab.json

@@ -0,0 +1 @@
+{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "E": 5, "A": 6, "O": 7, "S": 8, "N": 9, "R": 10, "L": 11, "I": 12, "D": 13, "U": 14, "T": 15, "C": 16, "M": 17, "P": 18, "B": 19, "Q": 20, "Y": 21, "H": 22, "G": 23, "V": 24, "Í": 25, "Á": 26, "F": 27, "Ó": 28, "J": 29, "É": 30, "Z": 31, "Ñ": 32, "X": 33, "Ú": 34, "'": 35, "K": 36, "W": 37, "Ü": 38, "-": 39}