初始化项目，由ModelHub XC社区提供模型

Model: sakares/wav2vec2-large-xlsr-thai-demo
Source: Original Platform

.gitattributes

@@ -0,0 +1,16 @@
+*.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

README.md

@@ -0,0 +1,137 @@
+---
+language: th
+datasets:
+- common_voice
+tags:
+- audio
+- automatic-speech-recognition
+- speech
+- xlsr-fine-tuning-week
+license: apache-2.0
+model-index:
+- name: XLSR Wav2Vec2 Large Thai by Sakares
+  results:
+  - task: 
+      name: Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: Common Voice th
+      type: common_voice
+      args: th  
+    metrics:
+       - name: Test WER
+         type: wer
+         value: 44.46
+---
+
+# Wav2Vec2-Large-XLSR-53-Thai
+
+Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) in Thai using the [Common Voice](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
+from pythainlp.tokenize import word_tokenize
+
+test_dataset = load_dataset("common_voice", "th", split="test[:2%]")
+
+processor = Wav2Vec2Processor.from_pretrained("sakares/wav2vec2-large-xlsr-thai-demo")
+model = Wav2Vec2ForCTC.from_pretrained("sakares/wav2vec2-large-xlsr-thai-demo")
+
+resampler = torchaudio.transforms.Resample(48_000, 16_000)
+
+## For Thai NLP Library, please feel free to check https://pythainlp.github.io/docs/2.2/api/tokenize.html
+def th_tokenize(batch):
+    batch["sentence"] = " ".join(word_tokenize(batch["sentence"], engine="newmm"))
+    return batch
+
+# 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).map(th_tokenize)
+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])
+```
+Usage script [here](https://colab.research.google.com/drive/1w0VywsBtjrO2pHHPmiPugYI9yeF8nUKg?usp=sharing)
+
+## Evaluation
+
+The model can be evaluated as follows on the {language} test data of Common Voice.
+
+
+```python
+import torch
+import torchaudio
+from datasets import load_dataset, load_metric
+from transformers import Wav2Vec2ForCTC, Wav2Vec2Processor
+from pythainlp.tokenize import word_tokenize
+import re
+
+test_dataset = load_dataset("common_voice", "th", split="test")
+wer = load_metric("wer")
+
+processor = Wav2Vec2Processor.from_pretrained("sakares/wav2vec2-large-xlsr-thai-demo")
+model = Wav2Vec2ForCTC.from_pretrained("sakares/wav2vec2-large-xlsr-thai-demo")
+model.to("cuda")
+
+chars_to_ignore_regex = '[\,\?\.\!\-\;\:\"\“]'
+resampler = torchaudio.transforms.Resample(48_000, 16_000)
+
+## For Thai NLP Library, please feel free to check https://pythainlp.github.io/docs/2.2/api/tokenize.html
+def th_tokenize(batch):
+    batch["sentence"] = " ".join(word_tokenize(batch["sentence"], engine="newmm"))
+    return batch
+
+# 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).map(th_tokenize)
+
+# 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**: 44.46 %
+Evaluate script [here](https://colab.research.google.com/drive/1WZGtHKWXBztRsuXHIdebf6uoAsp7rTnK?usp=sharing)
+
+## Training
+
+The Common Voice `train`, `validation` datasets were used for training.
+
+The script used for training can be found [here](https://colab.research.google.com/drive/18oUbeZgBGSkz16zC_WOa154QZOdmvjyt?usp=sharing)

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": 70,
+  "transformers_version": "4.4.0",
+  "vocab_size": 71
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb1f03e6996f45067b37846665462c9469495843102ce187588b897e28a7f4e
+size 2490659335

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 sha256:8cf9e30486947e5ed90fbee04baf77edce0daadf0effb971a783e7eee53f6215
+size 1262224919

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eadfc8ad40d25eb205d452eb44ca33a8d304d9199be7da405ad3378ff843c81
+size 623

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": "|"}

trainer_state.json

@@ -0,0 +1,142 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 23.83828382838284,
+  "global_step": 3600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.65,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 6.5741,
+      "step": 400
+    },
+    {
+      "epoch": 2.65,
+      "eval_loss": 3.4423439502716064,
+      "eval_runtime": 231.306,
+      "eval_samples_per_second": 9.459,
+      "eval_wer": 1.0,
+      "step": 400
+    },
+    {
+      "epoch": 5.3,
+      "learning_rate": 0.0002711907810499359,
+      "loss": 1.6231,
+      "step": 800
+    },
+    {
+      "epoch": 5.3,
+      "eval_loss": 0.6918022036552429,
+      "eval_runtime": 234.8428,
+      "eval_samples_per_second": 9.317,
+      "eval_wer": 0.7177260916407884,
+      "step": 800
+    },
+    {
+      "epoch": 7.94,
+      "learning_rate": 0.00023277848911651725,
+      "loss": 0.5103,
+      "step": 1200
+    },
+    {
+      "epoch": 7.94,
+      "eval_loss": 0.5981740951538086,
+      "eval_runtime": 233.6413,
+      "eval_samples_per_second": 9.365,
+      "eval_wer": 0.6444007858546169,
+      "step": 1200
+    },
+    {
+      "epoch": 10.59,
+      "learning_rate": 0.0001943661971830986,
+      "loss": 0.316,
+      "step": 1600
+    },
+    {
+      "epoch": 10.59,
+      "eval_loss": 0.6127611398696899,
+      "eval_runtime": 239.3303,
+      "eval_samples_per_second": 9.142,
+      "eval_wer": 0.6053615564991445,
+      "step": 1600
+    },
+    {
+      "epoch": 13.24,
+      "learning_rate": 0.0001559539052496799,
+      "loss": 0.227,
+      "step": 2000
+    },
+    {
+      "epoch": 13.24,
+      "eval_loss": 0.6392495036125183,
+      "eval_runtime": 236.7294,
+      "eval_samples_per_second": 9.243,
+      "eval_wer": 0.5767158882058432,
+      "step": 2000
+    },
+    {
+      "epoch": 15.89,
+      "learning_rate": 0.00011754161331626119,
+      "loss": 0.1783,
+      "step": 2400
+    },
+    {
+      "epoch": 15.89,
+      "eval_loss": 0.6448690891265869,
+      "eval_runtime": 240.8912,
+      "eval_samples_per_second": 9.083,
+      "eval_wer": 0.5625831801761836,
+      "step": 2400
+    },
+    {
+      "epoch": 18.54,
+      "learning_rate": 7.91293213828425e-05,
+      "loss": 0.1346,
+      "step": 2800
+    },
+    {
+      "epoch": 18.54,
+      "eval_loss": 0.6509573459625244,
+      "eval_runtime": 238.9168,
+      "eval_samples_per_second": 9.158,
+      "eval_wer": 0.5524431206033336,
+      "step": 2800
+    },
+    {
+      "epoch": 21.19,
+      "learning_rate": 4.071702944942381e-05,
+      "loss": 0.1149,
+      "step": 3200
+    },
+    {
+      "epoch": 21.19,
+      "eval_loss": 0.7118895053863525,
+      "eval_runtime": 239.1827,
+      "eval_samples_per_second": 9.148,
+      "eval_wer": 0.5582736548577223,
+      "step": 3200
+    },
+    {
+      "epoch": 23.84,
+      "learning_rate": 2.3047375160051214e-06,
+      "loss": 0.1024,
+      "step": 3600
+    },
+    {
+      "epoch": 23.84,
+      "eval_loss": 0.6984374523162842,
+      "eval_runtime": 239.7197,
+      "eval_samples_per_second": 9.127,
+      "eval_wer": 0.5488307243805057,
+      "step": 3600
+    }
+  ],
+  "max_steps": 3624,
+  "num_train_epochs": 24,
+  "total_flos": 1.4828294022260212e+19,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172c59484ed932416417e6a198f03373837732beb2793acc906d873aa5e63514
+size 2351

vocab.json

@@ -0,0 +1 @@
+{"ู": 0, "ั": 1, "ะ": 2, "ฆ": 3, "ำ": 4, "ึ": 5, "๋": 6, "ส": 7, "์": 8, "ฮ": 9, "ค": 10, "่": 11, "ผ": 12, "ศ": 13, "จ": 14, "ล": 15, "ฒ": 16, "ป": 17, "ม": 18, "็": 19, "’": 20, "ง": 21, "ํ": 22, "ฝ": 23, "ื": 24, "โ": 25, "ห": 26, "้": 27, "ษ": 29, "ๆ": 30, "า": 31, "ฟ": 32, "แ": 33, "ด": 34, "ท": 35, "ใ": 36, "ณ": 37, "ฬ": 38, "ไ": 39, "ๅ": 40, "อ": 41, "ี": 42, "๊": 43, "บ": 44, "ย": 45, "ิ": 46, "ฉ": 47, "ภ": 48, "ฏ": 49, "ข": 50, "ก": 51, "'": 52, "เ": 53, "พ": 54, "ฐ": 55, "ญ": 56, "น": 57, "ธ": 58, "ถ": 59, "ซ": 60, "ร": 61, "ฤ": 62, "ช": 63, "ุ": 64, "ต": 65, "ฑ": 66, "ฎ": 67, "ว": 68, "|": 28, "[UNK]": 69, "[PAD]": 70}