End of training

README.md

@@ -1,40 +1,36 @@
 ---
-language:
-- la
 license: mit
+base_model: facebook/w2v-bert-2.0
 tags:
 - generated_from_trainer
-datasets:
-- thiagolira/LatinYoutube
 metrics:
 - wer
-base_model: facebook/w2v-bert-2.0
 model-index:
 - name: CiceroASR
   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. -->
 
 # CiceroASR
 
-This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) 
-for the transcription of Classical Latin!
+This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5395
+- Wer: 0.2220
+
+## Model description
+
+More information needed
 
-Example from the Aeneid:
-<video controls src="https://cdn-uploads.huggingface.co/production/uploads/5fc7944e8a82cc0bcf7cc51d/hYNFr2od1EKDlRRdzJmzR.webm"></video>
-Transcription:
-**arma virumque cano** (Of arms and men I sing)
+## Intended uses & limitations
 
-Example from Genesis:
-<video controls src="https://cdn-uploads.huggingface.co/production/uploads/5fc7944e8a82cc0bcf7cc51d/9Q6DfG2h8FkABnl55DLBH.webm"></video>
-Transcription (little error there):
-**creavit deus chaelum et terram** (In the beggining God created the heaven and the earth)
+More information needed
 
+## Training and evaluation data
 
-It achieves the following results on the evaluation set of my dataset [Latin Youtube](https://huggingface.co/datasets/thiagolira/LatinYoutube):
-- Loss: 0.5026
-- Wer: 0.1651
+More information needed
 
 ## Training procedure
 
@@ -57,24 +53,26 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Wer    |
 |:-------------:|:-----:|:----:|:---------------:|:------:|
-| 2.9864        | 1.14  | 50   | 2.4639          | 1.0    |
-| 0.7134        | 2.27  | 100  | 0.4891          | 0.3601 |
-| 0.5196        | 3.41  | 150  | 0.5267          | 0.3022 |
-| 0.3779        | 4.55  | 200  | 0.4407          | 0.2369 |
-| 0.3818        | 5.68  | 250  | 0.4516          | 0.2360 |
-| 0.3           | 6.82  | 300  | 0.4365          | 0.2379 |
-| 0.3252        | 7.95  | 350  | 0.4238          | 0.2183 |
-| 0.2736        | 9.09  | 400  | 0.4609          | 0.2034 |
-| 0.1588        | 10.23 | 450  | 0.4007          | 0.2239 |
-| 0.1223        | 11.36 | 500  | 0.4892          | 0.1987 |
-| 0.0859        | 12.5  | 550  | 0.5393          | 0.1772 |
-| 0.0575        | 13.64 | 600  | 0.4629          | 0.1744 |
-| 0.0464        | 14.77 | 650  | 0.5026          | 0.1651 |
+| 3.6548        | 0.94  | 50   | 2.8634          | 0.9990 |
+| 2.2055        | 1.89  | 100  | 1.0921          | 0.9727 |
+| 1.667         | 2.83  | 150  | 0.7201          | 0.4615 |
+| 1.3148        | 3.77  | 200  | 0.6431          | 0.3866 |
+| 0.9899        | 4.72  | 250  | 0.5561          | 0.3116 |
+| 0.9629        | 5.66  | 300  | 0.6027          | 0.3817 |
+| 0.7557        | 6.6   | 350  | 0.7145          | 0.3145 |
+| 0.9143        | 7.55  | 400  | 0.4926          | 0.2610 |
+| 0.5837        | 8.49  | 450  | 0.5396          | 0.2619 |
+| 0.7037        | 9.43  | 500  | 0.5076          | 0.2746 |
+| 0.5986        | 10.38 | 550  | 0.5224          | 0.2415 |
+| 0.5288        | 11.32 | 600  | 0.5332          | 0.2259 |
+| 0.5034        | 12.26 | 650  | 0.5436          | 0.2249 |
+| 0.4897        | 13.21 | 700  | 0.5171          | 0.2162 |
+| 0.4738        | 14.15 | 750  | 0.5395          | 0.2220 |
 
 
 ### Framework versions
 
-- Transformers 4.38.0
+- Transformers 4.38.1
 - Pytorch 2.1.0+cu121
 - Datasets 2.17.1
-- Tokenizers 0.15.2
+- Tokenizers 0.15.2

config.json

@@ -9,7 +9,7 @@
   "architectures": [
     "Wav2Vec2BertForCTC"
   ],
-  "attention_dropout": 0.01,
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
   "classifier_proj_size": 768,
   "codevector_dim": 768,
@@ -30,14 +30,14 @@
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
+  "layerdrop": 0.1,
   "left_max_position_embeddings": 64,
   "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": 0.0,
+  "mask_time_prob": 0.05,
   "max_source_positions": 5000,
   "model_type": "wav2vec2-bert",
   "num_adapter_layers": 1,
@@ -47,7 +47,7 @@
   "num_hidden_layers": 24,
   "num_negatives": 100,
   "output_hidden_size": 1024,
-  "pad_token_id": 26,
+  "pad_token_id": 28,
   "position_embeddings_type": "relative_key",
   "proj_codevector_dim": 768,
   "right_max_position_embeddings": 8,
@@ -74,9 +74,9 @@
     1
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.38.0",
+  "transformers_version": "4.38.1",
   "use_intermediate_ffn_before_adapter": false,
   "use_weighted_layer_sum": false,
-  "vocab_size": 29,
+  "vocab_size": 31,
   "xvector_output_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d624783ea559e63e5ccbfeebf113f523d4392cca9f5b7c87c88fc6b1de66f24f
-size 2422933460
+oid sha256:e0b3ed488437a89e7f7698e03e1cb4024a3cdec1b502422e851d049a93c2271d
+size 2422945860

runs/Feb23_21-28-37_a1c0a7f9db93/events.out.tfevents.1708723755.a1c0a7f9db93.399.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55794fd39574b5d1aec9c9a815fb1c1c894f978cb20027394f512e6e8c2b2c95
+size 17640

runs/Feb23_21-50-41_a1c0a7f9db93/events.out.tfevents.1708725089.a1c0a7f9db93.399.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be87027f3a12f08445baa3f46e60af792834320cd20f19dbb16ccb24c1e3120d
+size 17467

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ef64dfc202d707f0f052d97cb9910b9c8c80ea2ffbf68cc9e4078fe8463c324
-size 4920
+oid sha256:7700e5ed7df84a1d2583138d2e5556600a67acb82570114f01dfea9cae123ba0
+size 4856