smutuvi/wav2vec2-large-xlsr-sw_ndizi_782_100_epoch

README.md

@@ -0,0 +1,83 @@
+---
+license: apache-2.0
+base_model: smutuvi/wav2vec2-large-xlsr-sw
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: wav2vec2-large-xlsr-sw_ndizi_782_100_epochs
+  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-large-xlsr-sw_ndizi_782_100_epochs
+
+This model is a fine-tuned version of [smutuvi/wav2vec2-large-xlsr-sw](https://huggingface.co/smutuvi/wav2vec2-large-xlsr-sw) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.1009
+- Wer: 0.4847
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 100
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 1.4035        | 4.79  | 400  | 1.2492          | 0.5608 |
+| 0.8489        | 9.58  | 800  | 1.0208          | 0.5114 |
+| 0.632         | 14.37 | 1200 | 1.3292          | 0.5306 |
+| 0.4653        | 19.16 | 1600 | 1.5159          | 0.5109 |
+| 0.3598        | 23.95 | 2000 | 1.4650          | 0.5450 |
+| 0.2776        | 28.74 | 2400 | 1.8568          | 0.5124 |
+| 0.218         | 33.53 | 2800 | 2.0913          | 0.5188 |
+| 0.1711        | 38.32 | 3200 | 2.2706          | 0.5035 |
+| 0.141         | 43.11 | 3600 | 2.3050          | 0.5094 |
+| 0.1162        | 47.9  | 4000 | 2.4539          | 0.5025 |
+| 0.1007        | 52.69 | 4400 | 2.4754          | 0.5020 |
+| 0.0881        | 57.49 | 4800 | 2.5512          | 0.5030 |
+| 0.0816        | 62.28 | 5200 | 2.6458          | 0.5064 |
+| 0.0792        | 67.07 | 5600 | 2.7869          | 0.5025 |
+| 0.06          | 71.86 | 6000 | 2.9063          | 0.5040 |
+| 0.0594        | 76.65 | 6400 | 2.8363          | 0.5049 |
+| 0.0527        | 81.44 | 6800 | 3.0801          | 0.4921 |
+| 0.0473        | 86.23 | 7200 | 3.0959          | 0.4867 |
+| 0.0471        | 91.02 | 7600 | 3.0942          | 0.4852 |
+| 0.0405        | 95.81 | 8000 | 3.1009          | 0.4847 |
+
+
+### Framework versions
+
+- Transformers 4.37.1
+- Pytorch 2.2.1+cu118
+- Datasets 2.16.1
+- Tokenizers 0.15.0

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 60,
+  "<s>": 59
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b176dab8648b9b163cbafe7f51d35dd6060de96f4c31f4f996ce8d3f6e7a89b1
+oid sha256:5c061c03b90ba153cdd6765384ddb007ed10b0cdbcee804bc0a84865cc21ac33
 size 1262057580

preprocessor_config.json

@@ -4,6 +4,7 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0.0,
+  "processor_class": "Wav2Vec2Processor",
   "return_attention_mask": true,
   "sampling_rate": 16000
 }

runs/Mar22_05-32-55_hades-prod01/events.out.tfevents.1711085640.hades-prod01.437015.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d943f60bc64d15b6ea55295b55b696e7f83db31dfedb7ec8222444e5ac3df17
-size 15620
+oid sha256:0dff4db984a7efbc25a5d02f7ffe2167e23b33b2b295c8cb932c7e6c26e63477
+size 15974

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "57": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "60": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,61 @@
+{
+  "'": 35,
+  "(": 33,
+  ")": 5,
+  "*": 52,
+  "/": 48,
+  "=": 44,
+  "[PAD]": 58,
+  "[UNK]": 57,
+  "_": 18,
+  "`": 6,
+  "a": 51,
+  "b": 16,
+  "c": 37,
+  "d": 28,
+  "e": 24,
+  "f": 54,
+  "g": 56,
+  "h": 30,
+  "i": 17,
+  "j": 3,
+  "k": 19,
+  "l": 47,
+  "m": 55,
+  "n": 23,
+  "o": 21,
+  "p": 1,
+  "q": 34,
+  "r": 50,
+  "s": 4,
+  "t": 0,
+  "u": 22,
+  "v": 26,
+  "w": 15,
+  "x": 2,
+  "y": 53,
+  "z": 11,
+  "|": 14,
+  "°": 43,
+  "µ": 46,
+  "á": 12,
+  "â": 41,
+  "ã": 45,
+  "å": 7,
+  "é": 36,
+  "ë": 49,
+  "í": 39,
+  "ï": 38,
+  "ñ": 13,
+  "ó": 9,
+  "ö": 29,
+  "ø": 27,
+  "ú": 40,
+  "š": 31,
+  "ū": 8,
+  "ː": 25,
+  "ụ": 10,
+  "’": 32,
+  "•": 42,
+  "…": 20
+}