Upload 7 files

README.md

@@ -1,3 +1,69 @@
 ---
-license: unknown
+tags:
+- automatic-speech-recognition
+- ahazeemi/librispeech10h
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: wavlm-libri-clean-100h-large
+  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. -->
+
+# wavlm-libri-clean-100h-large
+
+This model is a fine-tuned version of [microsoft/wavlm-large](https://huggingface.co/microsoft/wavlm-large) on the AHAZEEMI/LIBRISPEECH10H - CLEAN dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0893
+- Wer: 0.0655
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.0144        | 0.42  | 300  | 0.0947          | 0.0749 |
+| 0.1408        | 0.84  | 600  | 0.1347          | 0.1363 |
+| 0.0396        | 1.26  | 900  | 0.1090          | 0.0935 |
+| 0.0353        | 1.68  | 1200 | 0.1032          | 0.0832 |
+| 0.051         | 2.1   | 1500 | 0.0969          | 0.0774 |
+| 0.0254        | 2.52  | 1800 | 0.0930          | 0.0715 |
+| 0.0579        | 2.94  | 2100 | 0.0894          | 0.0660 |
+
+
+### Framework versions
+
+- Transformers 4.26.1
+- Pytorch 2.0.0+cpu
+- Datasets 2.9.0
+- Tokenizers 0.13.2

special_tokens_map.json

@@ -0,0 +1,22 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "./wavlm-libri-clean-100h-large",
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.05018302534102554,
+    "train_runtime": 453623.4225,
+    "train_samples": 2853,
+    "train_samples_per_second": 0.019,
+    "train_steps_per_second": 0.005
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76461c865019fa3e7873f5a6486e2cb9f2d2d07b911cba04c823bb74440ed581
+size 3515

vocab.json

@@ -0,0 +1,31 @@
+{
+  "[PAD]": 28,
+  "[UNK]": 27,
+  "a": 1,
+  "b": 2,
+  "c": 3,
+  "d": 4,
+  "e": 5,
+  "f": 6,
+  "g": 7,
+  "h": 8,
+  "i": 9,
+  "j": 10,
+  "k": 11,
+  "l": 12,
+  "m": 13,
+  "n": 14,
+  "o": 15,
+  "p": 16,
+  "q": 17,
+  "r": 18,
+  "s": 19,
+  "t": 20,
+  "u": 21,
+  "v": 22,
+  "w": 23,
+  "x": 24,
+  "y": 25,
+  "z": 26,
+  "|": 0
+}