Added model files

README.md

@@ -1,3 +1,67 @@
----
-license: mit
----
+---
+language:
+- lg
+license: apache-2.0
+tags:
+- automatic-speech-recognition
+- robust-speech-event
+- common_voice
+- generated_from_trainer
+datasets:
+- common_voice
+model-index:
+- name: wav2vec2-xls-r-300m-lg
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# wav2vec2-xls-r-300m-lg
+
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the COMMON_VOICE - LG dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6989
+- Wer: 0.8529
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0003
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 2.9089        | 6.33  | 500  | 2.8983          | 1.0002 |
+| 2.5754        | 12.66 | 1000 | 1.8710          | 1.0    |
+| 1.4093        | 18.99 | 1500 | 0.7195          | 0.8547 |
+
+
+### Framework versions
+
+- Transformers 4.17.0.dev0
+- Pytorch 1.10.2+cu102
+- Datasets 1.18.2.dev0
+- Tokenizers 0.11.0

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 33, "</s>": 34}

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.6989022493362427,
+    "eval_runtime": 32.5515,
+    "eval_samples": 584,
+    "eval_samples_per_second": 17.941,
+    "eval_steps_per_second": 2.243,
+    "eval_wer": 0.8528689439607056,
+    "train_loss": 2.2397680982758725,
+    "train_runtime": 1536.9705,
+    "train_samples": 1250,
+    "train_samples_per_second": 16.266,
+    "train_steps_per_second": 1.028
+}

checkpoint-1500/config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "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": "mean",
+  "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": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 64,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.25,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.75,
+  "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": 32,
+  "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": "4.17.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 35,
+  "xvector_output_dim": 512
+}

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21d904218540109689239922280a946662ee011edd86bec251c7370527ad4941
+size 2490346001

checkpoint-1500/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
+}

checkpoint-1500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69fb5a065fa6ed0677cba6583748fa75bdefb5c4126396fdf1dff68d7c8a5943
+size 1262067185

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ce7cd11c07d3a00656a6d4bdbcdfd5c7a8cd5e7becd311130665efa84940439
+size 14567

checkpoint-1500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0040f974cd0e823a8165d65b98a5e051372bd49cadf90ec18b3f906cfc158652
+size 559

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26e2196ad298cf0d91f1828a2047a2d1124469a2f33874fb3fecd0f1e4c6a57e
+size 623

checkpoint-1500/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 18.9873417721519,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 6.33,
+      "learning_rate": 0.00020544303797468352,
+      "loss": 2.9089,
+      "step": 500
+    },
+    {
+      "epoch": 6.33,
+      "eval_loss": 2.89827823638916,
+      "eval_runtime": 29.5705,
+      "eval_samples_per_second": 19.749,
+      "eval_steps_per_second": 2.469,
+      "eval_wer": 1.0002232641214557,
+      "step": 500
+    },
+    {
+      "epoch": 12.66,
+      "learning_rate": 0.00011069620253164557,
+      "loss": 2.5754,
+      "step": 1000
+    },
+    {
+      "epoch": 12.66,
+      "eval_loss": 1.8709616661071777,
+      "eval_runtime": 29.8131,
+      "eval_samples_per_second": 19.589,
+      "eval_steps_per_second": 2.449,
+      "eval_wer": 1.0,
+      "step": 1000
+    },
+    {
+      "epoch": 18.99,
+      "learning_rate": 1.5759493670886074e-05,
+      "loss": 1.4093,
+      "step": 1500
+    },
+    {
+      "epoch": 18.99,
+      "eval_loss": 0.7194529175758362,
+      "eval_runtime": 29.359,
+      "eval_samples_per_second": 19.892,
+      "eval_steps_per_second": 2.486,
+      "eval_wer": 0.854655056932351,
+      "step": 1500
+    }
+  ],
+  "max_steps": 1580,
+  "num_train_epochs": 20,
+  "total_flos": 3.455573616051334e+18,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e62690eea4d37160aab77e872f33e76a037a328dce161d3049151e0e9074debf
+size 3055

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "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": "mean",
+  "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": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 64,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.25,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.75,
+  "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": 32,
+  "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": "4.17.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 35,
+  "xvector_output_dim": 512
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 0.6989022493362427,
+    "eval_runtime": 32.5515,
+    "eval_samples": 584,
+    "eval_samples_per_second": 17.941,
+    "eval_steps_per_second": 2.243,
+    "eval_wer": 0.8528689439607056
+}

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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a45355a5682445e5357a871c321461901a9260a46405d104da422725d95f2c
+size 1262067185

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

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": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./wav2vec2-xls-r-300m-lg", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "train_loss": 2.2397680982758725,
+    "train_runtime": 1536.9705,
+    "train_samples": 1250,
+    "train_samples_per_second": 16.266,
+    "train_steps_per_second": 1.028
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "global_step": 1580,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 6.33,
+      "learning_rate": 0.00020544303797468352,
+      "loss": 2.9089,
+      "step": 500
+    },
+    {
+      "epoch": 6.33,
+      "eval_loss": 2.89827823638916,
+      "eval_runtime": 29.5705,
+      "eval_samples_per_second": 19.749,
+      "eval_steps_per_second": 2.469,
+      "eval_wer": 1.0002232641214557,
+      "step": 500
+    },
+    {
+      "epoch": 12.66,
+      "learning_rate": 0.00011069620253164557,
+      "loss": 2.5754,
+      "step": 1000
+    },
+    {
+      "epoch": 12.66,
+      "eval_loss": 1.8709616661071777,
+      "eval_runtime": 29.8131,
+      "eval_samples_per_second": 19.589,
+      "eval_steps_per_second": 2.449,
+      "eval_wer": 1.0,
+      "step": 1000
+    },
+    {
+      "epoch": 18.99,
+      "learning_rate": 1.5759493670886074e-05,
+      "loss": 1.4093,
+      "step": 1500
+    },
+    {
+      "epoch": 18.99,
+      "eval_loss": 0.7194529175758362,
+      "eval_runtime": 29.359,
+      "eval_samples_per_second": 19.892,
+      "eval_steps_per_second": 2.486,
+      "eval_wer": 0.854655056932351,
+      "step": 1500
+    },
+    {
+      "epoch": 20.0,
+      "step": 1580,
+      "total_flos": 3.6376414033360364e+18,
+      "train_loss": 2.2397680982758725,
+      "train_runtime": 1536.9705,
+      "train_samples_per_second": 16.266,
+      "train_steps_per_second": 1.028
+    }
+  ],
+  "max_steps": 1580,
+  "num_train_epochs": 20,
+  "total_flos": 3.6376414033360364e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e62690eea4d37160aab77e872f33e76a037a328dce161d3049151e0e9074debf
+size 3055

vocab.json

@@ -0,0 +1 @@
+{"!": 1, "\"": 2, "'": 3, ",": 4, ".": 5, "?": 6, "a": 7, "b": 8, "c": 9, "d": 10, "e": 11, "f": 12, "g": 13, "h": 14, "i": 15, "j": 16, "k": 17, "l": 18, "m": 19, "n": 20, "o": 21, "p": 22, "r": 23, "s": 24, "t": 25, "u": 26, "v": 27, "w": 28, "y": 29, "z": 30, "|": 0, "[UNK]": 31, "[PAD]": 32}