wav2vec2-base-chichewa

README.md

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: openai/whisper-medium
+base_model: facebook/wav2vec2-base
 tags:
 - generated_from_trainer
 model-index:
@@ -14,16 +14,16 @@ should probably proofread and complete it, then remove this comment. -->
 
 # output
 
-This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
+This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.3212
-- eval_wer: 0.2444
-- eval_cer: 0.0692
-- eval_runtime: 422.9731
-- eval_samples_per_second: 1.012
-- eval_steps_per_second: 0.128
-- epoch: 1.7130
-- step: 3477
+- eval_loss: 1.3522
+- eval_wer: 0.5850
+- eval_cer: 0.1843
+- eval_runtime: 12.6829
+- eval_samples_per_second: 7.333
+- eval_steps_per_second: 0.946
+- epoch: 89.2857
+- step: 5000
 
 ## Model description
 
@@ -42,16 +42,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-06
-- train_batch_size: 2
+- learning_rate: 0.0001
+- train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 4
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 500
-- training_steps: 5000
+- lr_scheduler_warmup_steps: 1000
+- training_steps: 10000
 - mixed_precision_training: Native AMP
 
 ### Framework versions

config.json

@@ -1,61 +1,118 @@
 {
-  "_name_or_path": "openai/whisper-medium",
+  "_name_or_path": "facebook/wav2vec2-base",
   "activation_dropout": 0.0,
-  "activation_function": "gelu",
-  "apply_spec_augment": false,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
   "architectures": [
-    "WhisperForConditionalGeneration"
+    "Wav2Vec2ForCTC"
   ],
-  "attention_dropout": 0.0,
-  "begin_suppress_tokens": null,
-  "bos_token_id": 50257,
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
   "classifier_proj_size": 256,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 24,
-  "decoder_start_token_id": 50258,
-  "dropout": 0.0,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 24,
-  "eos_token_id": 50257,
-  "forced_decoder_ids": [
-    [
-      1,
-      50259
-    ],
-    [
-      2,
-      50359
-    ],
-    [
-      3,
-      50363
-    ]
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
   ],
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
+  "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,
-  "max_length": null,
-  "max_source_positions": 1500,
-  "max_target_positions": 448,
-  "median_filter_width": 7,
-  "model_type": "whisper",
-  "num_hidden_layers": 24,
-  "num_mel_bins": 80,
-  "pad_token_id": 50257,
-  "scale_embedding": false,
+  "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": 40,
+  "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": "4.48.0",
-  "use_cache": false,
   "use_weighted_layer_sum": false,
-  "vocab_size": 51865
+  "vocab_size": 43,
+  "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77b5fc5d06d1e63583b68dfbc2f1d90a8390768af5cc5cf7b0fe9de6c4c2f3ab
-size 3055544304
+oid sha256:20f055dc599802a2a1807df0c29fed6a88d682e92de61c2971d0a9e24908667a
+size 377644964

runs/Nov16_14-42-35_77681a92cda5/events.out.tfevents.1763304214.77681a92cda5.2247.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e96757058a5c81c61aec1fb88658cd628d4a37c71f1736b8f77dd1bb29f1c475
+size 12519

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4e75c45b5d2941781efbe0987bee377a6e4ea5fdbc34ff1264c52c1fe14d3d3
-size 5905
+oid sha256:1fef0844fb4dc2dc76f90304ae30b82ac5c431df8bd39d16f3abde32622b9016
+size 5713