patrickvonplaten
commited on
Commit
•
bf9b1e6
1
Parent(s):
a1b0827
upload
Browse files- config.json +1 -1
- preprocessor_config.json +9 -0
- pytorch_model.bin +1 -1
- run.sh +2 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- vocab.json +1 -0
config.json
CHANGED
@@ -47,5 +47,5 @@
|
|
47 |
"num_hidden_layers": 2,
|
48 |
"pad_token_id": 0,
|
49 |
"transformers_version": "4.6.0.dev0",
|
50 |
-
"vocab_size":
|
51 |
}
|
47 |
"num_hidden_layers": 2,
|
48 |
"pad_token_id": 0,
|
49 |
"transformers_version": "4.6.0.dev0",
|
50 |
+
"vocab_size": 12
|
51 |
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_extractor_type": "Wav2Vec2FeatureExtractor",
|
4 |
+
"feature_size": 1,
|
5 |
+
"padding_side": "right",
|
6 |
+
"padding_value": 0.0,
|
7 |
+
"return_attention_mask": false,
|
8 |
+
"sampling_rate": 16000
|
9 |
+
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1233503
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40bff8e06f2ac9a5931ed60695d028ef72168eab7933427900a90ffb6ec76a03
|
3 |
size 1233503
|
run.sh
ADDED
@@ -0,0 +1,2 @@
|
|
|
|
|
1 |
+
#!/usr/bin/env bash
|
2 |
+
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
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|"}
|
vocab.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"a": 0, "b": 1, "c": 2, "d": 3, "e": 4, "f": 5, "g": 6, "<s>": 7, "</s>": 8, "<unk>": 9, "<pad>": 10, "|": 11}
|