Upload 6 files

wav2vecChinese/README.md

@@ -0,0 +1,61 @@
+---
+license: mit
+---
+Pretrained on 10k hours WenetSpeech L subset. More details in  [TencentGameMate/chinese_speech_pretrain](https://github.com/TencentGameMate/chinese_speech_pretrain)
+
+This model does not have a tokenizer as it was pretrained on audio alone. 
+In order to use this model speech recognition, a tokenizer should be created and the model should be fine-tuned on labeled text data.
+
+python package:
+transformers==4.16.2
+
+```python
+
+
+import torch
+import torch.nn.functional as F
+import soundfile as sf
+from fairseq import checkpoint_utils
+
+from transformers import (
+    Wav2Vec2FeatureExtractor,
+    Wav2Vec2ForPreTraining,
+    Wav2Vec2Model,
+)
+from transformers.models.wav2vec2.modeling_wav2vec2 import _compute_mask_indices
+
+model_path=""
+wav_path=""
+mask_prob=0.0
+mask_length=10
+
+feature_extractor = Wav2Vec2FeatureExtractor.from_pretrained(model_path)
+model = Wav2Vec2Model.from_pretrained(model_path)
+
+# for pretrain: Wav2Vec2ForPreTraining
+# model = Wav2Vec2ForPreTraining.from_pretrained(model_path)
+
+model = model.to(device)
+model = model.half()
+model.eval()
+
+wav, sr = sf.read(wav_path)
+input_values = feature_extractor(wav, return_tensors="pt").input_values
+input_values = input_values.half()
+input_values = input_values.to(device)
+
+# for Wav2Vec2ForPreTraining
+# batch_size, raw_sequence_length = input_values.shape
+# sequence_length = model._get_feat_extract_output_lengths(raw_sequence_length)
+# mask_time_indices = _compute_mask_indices((batch_size, sequence_length), mask_prob=0.0, mask_length=2)
+# mask_time_indices = torch.tensor(mask_time_indices, device=input_values.device, dtype=torch.long)
+
+with torch.no_grad():
+    outputs = model(input_values)
+    last_hidden_state = outputs.last_hidden_state
+
+    # for Wav2Vec2ForPreTraining
+    # outputs = model(input_values, mask_time_indices=mask_time_indices, output_hidden_states=True)
+    # last_hidden_state = outputs.hidden_states[-1]
+
+```

wav2vecChinese/config.json

@@ -0,0 +1,115 @@
+{
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForPreTraining"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "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": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "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": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "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_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.075,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

wav2vecChinese/gitattributes.txt

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet 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
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

wav2vecChinese/hyperparams.yaml

@@ -0,0 +1,59 @@
+# ############################################################################
+# Model: WAV2VEC base for Emotion Recognition
+# ############################################################################
+
+
+# Hparams NEEDED
+HPARAMS_NEEDED: ["encoder_dim", "out_n_neurons", "label_encoder", "softmax"]
+# Modules Needed
+MODULES_NEEDED: ["wav2vec2", "avg_pool", "output_mlp"]
+
+# Feature parameters
+wav2vec2_hub: wav2vecChinese
+
+# Pretrain folder (HuggingFace)
+pretrained_path: emotion-recognition-wav2vec2-IEMOCAP
+
+# parameters
+encoder_dim: 768
+out_n_neurons: 4
+
+wav2vec2: !new:speechbrain.lobes.models.huggingface_wav2vec.HuggingFaceWav2Vec2
+    source: D:/pycharm2020/code/yuyin_ChineseWav2vec/pretrained_models/facebook/wav2vec2-base
+    output_norm: True
+    freeze: True
+    save_path: wav2vec2_checkpoints
+
+avg_pool: !new:speechbrain.nnet.pooling.StatisticsPooling
+    return_std: False
+
+output_mlp: !new:speechbrain.nnet.linear.Linear
+    input_size: !ref <encoder_dim>
+    n_neurons: !ref <out_n_neurons>
+    bias: False
+
+model: !new:torch.nn.ModuleList
+    - [!ref <output_mlp>]
+
+modules:
+    wav2vec2: !ref <wav2vec2>
+    output_mlp: !ref <output_mlp>
+    avg_pool: !ref <avg_pool>
+
+softmax: !new:speechbrain.nnet.activations.Softmax
+
+        
+label_encoder: !new:speechbrain.dataio.encoder.CategoricalEncoder
+
+
+pretrainer: !new:speechbrain.utils.parameter_transfer.Pretrainer
+    loadables:
+        wav2vec2: !ref <wav2vec2>
+        model: !ref <model>
+        label_encoder: !ref <label_encoder>
+    paths:
+        wav2vec2: !ref <pretrained_path>/wav2vec2.ckpt
+        model: !ref <pretrained_path>/model.ckpt
+        label_encoder: !ref <pretrained_path>/label_encoder.txt
+
+

wav2vecChinese/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

wav2vecChinese/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8a5554a79c3bbbe76f2e43d3d4b4369c8c2abd5515e623192e0381d7e5e7b3f
+size 1269726951