dima1234321/wav2vec2-xls-r-300m-phoneme_he_small1

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+test_dataset filter=lfs diff=lfs merge=lfs -text
+train_dataset filter=lfs diff=lfs merge=lfs -text
+valid_dataset filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,73 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-xls-r-300m
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: shared_audio
+  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. -->
+
+# shared_audio
+
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 19.5815
+- Wer: 1.0
+- Cer: 1.0
+
+## 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: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 20
+- training_steps: 100
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer | Cer    |
+|:-------------:|:-----:|:----:|:---------------:|:---:|:------:|
+| 62.6565       | 0.16  | 10   | 63.7309         | 1.0 | 2.9738 |
+| 46.9251       | 0.32  | 20   | 54.7811         | 1.0 | 1.0    |
+| 43.8044       | 0.48  | 30   | 32.9802         | 1.0 | 1.0    |
+| 30.6358       | 0.64  | 40   | 26.5389         | 1.0 | 1.0    |
+| 23.5351       | 0.8   | 50   | 23.3499         | 1.0 | 1.0    |
+| 29.7649       | 0.96  | 60   | 21.5416         | 1.0 | 1.0    |
+| 21.3599       | 1.12  | 70   | 20.5404         | 1.0 | 1.0    |
+| 19.8412       | 1.28  | 80   | 19.8837         | 1.0 | 1.0    |
+| 23.5039       | 1.44  | 90   | 19.5565         | 1.0 | 1.0    |
+| 20.1719       | 1.6   | 100  | 19.4386         | 1.0 | 1.0    |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,109 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "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": "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,
+  "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": 0.0,
+  "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": 101,
+  "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": "4.38.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 104,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83096bb2075586342fa0703c2cf4e1d8c4124779a58c55deb8bc2e65bd53b13b
+size 1262233880

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

runs/Mar15_09-45-00_9163490853ac/events.out.tfevents.1710496114.9163490853ac.482.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323678ff51d2c5e5d2a9028112301b5feb190cc9c6fc7ba06fbdea77986e9f40
+size 30701

runs/Mar15_09-45-00_9163490853ac/events.out.tfevents.1710509183.9163490853ac.482.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a7339d1983396c0dc65de5a4fdae35cf6f97f9e54344016c0cad27a28b81b14
+size 446

test_dataset

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fc1ca3d0a8985e3553cccebf80a340f42aa8ce3a1de725c7c63128bbf3e3d5b
+size 52862488

train_dataset

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8195a87c464ca3ed145693a7aec9878f7626c4ca49ec53f6c4912033db87f2d
+size 415167252

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92e96185dc6b382024930bfbbd505f2b7aed9db60a71e6eecf8e372096d5d0f2
+size 4920

valid_dataset

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33f54ac6a4bdaad37735a7424c22e4745448c9b1811825191feff4886ebf2e56
+size 52189620

vocab.json

@@ -0,0 +1 @@
+{"a": 1, "b": 2, "ba": 3, "be": 4, "bi": 5, "bo": 6, "bu": 7, "d": 8, "da": 9, "de": 10, "di": 11, "do": 12, "du": 13, "e": 14, "f": 15, "g": 16, "ga": 17, "ge": 18, "gi": 19, "go": 20, "gu": 21, "h": 22, "ha": 23, "he": 24, "hi": 25, "ho": 26, "hu": 27, "i": 28, "k": 29, "ka": 30, "ke": 31, "ki": 32, "ko": 33, "ku": 34, "l": 35, "la": 36, "le": 37, "li": 38, "lo": 39, "lu": 40, "m": 41, "n": 42, "o": 43, "p": 44, "pa": 45, "pe": 46, "pi": 47, "po": 48, "pu": 49, "r": 50, "ra": 51, "re": 52, "ri": 53, "ro": 54, "ru": 55, "s": 56, "sa": 57, "se": 58, "sh": 59, "sha": 60, "she": 61, "shi": 62, "sho": 63, "shu": 64, "si": 65, "so": 66, "su": 67, "t": 68, "ta": 69, "te": 70, "ti": 71, "to": 72, "tu": 73, "tz": 74, "u": 75, "v": 76, "va": 77, "ve": 78, "vi": 79, "vo": 80, "vu": 81, "x": 82, "xa": 83, "xe": 84, "xi": 85, "xo": 86, "xu": 87, "y": 88, "ya": 89, "ye": 90, "yi": 91, "yo": 92, "yu": 93, "z": 94, "za": 95, "ze": 96, "zi": 97, "zo": 98, "zu": 99, "|": 0, "[UNK]": 100, "[PAD]": 101}