initial commit

.gitignore

@@ -0,0 +1 @@
+cv-corpus-6.1-2020-12-11

README.md

@@ -0,0 +1,62 @@
+---
+language: mn
+datasets:
+- common_voice
+tags:
+- speech
+- audio
+- automatic-speech-recognition
+license: apache-2.0
+---
+
+## Evaluation on Common Voice Mongolian Test
+```python
+import torchaudio
+from datasets import load_dataset, load_metric
+from transformers import (
+    Wav2Vec2ForCTC,
+    Wav2Vec2Processor,
+)
+import torch
+import re
+import sys
+
+model_name = "tugstugi/wav2vec2-large-xlsr-53-mongolian"
+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", "mn", 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**: 50.0 %

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": 37,
+  "transformers_version": "4.4.0.dev0",
+  "vocab_size": 38
+}

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:a47ec4a791b0fd90d62b19a0eaa3a6a8875661f796dda6b6049205c55f862869
+size 1262089623

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 @@
+{"г": 0, "ү": 1, "ю": 2, "р": 3, "д": 4, "е": 5, "э": 6, "ъ": 7, "л": 8, "в": 9, "м": 10, "ө": 11, "т": 12, "ц": 13, "о": 14, "а": 16, "к": 17, "ф": 18, "и": 19, "ш": 20, "я": 21, "h": 22, "з": 23, "ё": 24, "с": 25, "ы": 26, "п": 27, "х": 28, "ж": 29, "ь": 30, "й": 31, "у": 32, "н": 33, "б": 34, "ч": 35, "|": 15, "[UNK]": 36, "[PAD]": 37}