Upload folder using huggingface_hub

.gitattributes

@@ -2,34 +2,26 @@
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt 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
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz 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
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl 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
-*.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* 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
-*.zst filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

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]
+
+```

chinese-wav2vec2-base-fairseq-ckpt.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a75e04e426977dd399415b7f586b18978bc6836a3e8514ae1bb29e468fb17184
+size 1140632401

config.json

@@ -0,0 +1,105 @@
+{
+  "activation_dropout": 0.1,
+  "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": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "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": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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_prob": 0.05,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "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": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "proj_codevector_dim": 256,
+  "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
+}

preprocessor_config.json

@@ -0,0 +1,8 @@
+{
+  "do_normalize": false,
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be2da40c9e7ae26bfc904a3ed79ebb9e8f060bec6dba85d6a6ae86114bc38901
+size 380261837