End of training

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+base_model: facebook/wav2vec2-large-xlsr-53
+tags:
+- generated_from_trainer
+model-index:
+- name: Runyakore_XlSR_WAV2VEC
+  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. -->
+
+# Runyakore_XlSR_WAV2VEC
+
+This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the None dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 0.4952
+- eval_wer: 0.5667
+- eval_runtime: 16.7338
+- eval_samples_per_second: 5.737
+- eval_steps_per_second: 0.717
+- epoch: 5.4
+- step: 13000
+
+## 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: 0.0001
+- train_batch_size: 2
+- 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: 500
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 36,
+  "<s>": 35
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5649c571884cb892e2978ebd3749e38b5b9711ecf24ead648d1df33d9017dd5
+oid sha256:c5b849a7ae49a6112b67d5543b42d543109cc5536856aed363d4269a57a8ccaf
 size 1261959180

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/Feb06_16-47-28_b3ce89a1c4cd/events.out.tfevents.1707238264.b3ce89a1c4cd.2195.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ae7e73687a2831e61f47f06db424d3c614779f41107894d6234f2620a50488e
-size 91881
+oid sha256:fa1cc66c14791d6c4b0c0366025b37640f01e787f4ac32ee2925d6af9b59e65f
+size 93294

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "33": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "36": {
+      "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 +1,37 @@
+{
+  "'": 1,
+  "/": 20,
+  "1": 2,
+  "3": 10,
+  "8": 6,
+  "9": 16,
+  "[PAD]": 34,
+  "[UNK]": 33,
+  "a": 31,
+  "b": 11,
+  "c": 15,
+  "d": 12,
+  "e": 13,
+  "f": 19,
+  "g": 22,
+  "h": 3,
+  "i": 32,
+  "j": 29,
+  "k": 4,
+  "l": 30,
+  "m": 8,
+  "n": 17,
+  "o": 23,
+  "p": 28,
+  "r": 0,
+  "s": 9,
+  "t": 27,
+  "u": 7,
+  "v": 18,
+  "w": 24,
+  "x": 21,
+  "y": 5,
+  "z": 14,
+  "|": 25,
+  "’": 26
+}