End of training

README.md

@@ -0,0 +1,49 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- alffa_amharic
+model-index:
+- name: asr-amharic-phoneme-based-39
+  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. -->
+
+# asr-amharic-phoneme-based-39
+
+This model was trained from scratch on the alffa_amharic dataset.
+
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 30
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,118 @@
+{
+  "_name_or_path": "/content/gdrive/MyDrive/Wav2Vec_model/asr-amharic-phoneme-based-39/checkpoint-4800",
+  "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": 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": "mean",
+  "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": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "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": "4.35.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 39,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15de71319b5fa318b942fe200d2a8824697e3000213507fc023abca1b7205a4f
+size 377632660

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": false,
+  "sampling_rate": 16000
+}

runs/Dec20_16-50-32_6a52e7eafeb2/events.out.tfevents.1703091465.6a52e7eafeb2.1244.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8e090fbe5ac340bceabebeb308fc666b3d931eae7e532bc3b065675cb09f5a8
+size 442941

runs/vocab_phoneme.json

@@ -0,0 +1,41 @@
+{
+    "[PAD]": 0,
+    "[UNK]": 38,
+    "|": 29,
+    "ህ": 3,
+    "ል": 19,
+    "ም": 30,
+    "ር": 18,
+    "ስ": 17,
+    "ሽ": 36,
+    "ቅ": 35,
+    "ብ": 28,
+    "ቭ": 10,
+    "ት": 23,
+    "ች": 32,
+    "ን": 24,
+    "ኝ": 4,
+    "ኡ": 12,
+    "ኢ": 34,
+    "ኣ": 9,
+    "ኤ": 20,
+    "እ": 22,
+    "ኦ": 5,
+    "ኧ": 11,
+    "ክ": 16,
+    "ኰ": 26,
+    "ኸ": 8,
+    "ው": 6,
+    "ዝ": 15,
+    "ዥ": 2,
+    "ይ": 33,
+    "ድ": 21,
+    "ጅ": 13,
+    "ግ": 14,
+    "ጥ": 7,
+    "ጭ": 31,
+    "ጵ": 27,
+    "ጽ": 25,
+    "ፍ": 37,
+    "ፕ": 1
+  }

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e865cc1021fa9c8e220b20d803c5379f7478377a46edc73f1acfbf799fbc7120
+size 4664