upload

config.json

@@ -47,5 +47,5 @@
   "num_hidden_layers": 2,
   "pad_token_id": 0,
   "transformers_version": "4.6.0.dev0",
-  "vocab_size": 32
+  "vocab_size": 12
 }

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:487f6322674b5e608eb056e6b3d5c210abd3d04258137e59a4e6c83139cdf46d
+oid sha256:40bff8e06f2ac9a5931ed60695d028ef72168eab7933427900a90ffb6ec76a03
 size 1233503

run.sh

@@ -0,0 +1,2 @@
+#!/usr/bin/env bash
+python ../transformers/examples/research_projects/wav2vec2/run_asr.py --output_dir=output_dir --num_train_epochs=1 --per_device_train_batch_size=2 --per_device_eval_batch_size=2 --evaluation_strategy=steps --save_steps=500 --eval_steps=100 --logging_steps=50 --learning_rate=5e-4 --warmup_steps=3000 --model_name_or_path=./wav2vec2_tiny_random_robust --dataset_name=patrickvonplaten/librispeech_asr_dummy --dataset_config_name=clean --train_split_name=validation --validation_split_name=validation --orthography=timit --preprocessing_num_workers=1 --group_by_length --freeze_feature_extractor --verbose_logging

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|"}

vocab.json

@@ -0,0 +1 @@
+{"a": 0, "b": 1, "c": 2, "d": 3, "e": 4, "f": 5, "g": 6, "<s>": 7, "</s>": 8, "<unk>": 9, "<pad>": 10, "|": 11}