2 contributors

History: 23 commits

xezpeleta

Update the learning rate hyperparameter

37c4f69 over 1 year ago

runs
End of training over 1 year ago
.gitattributes

1.52 kB

initial commit over 1 year ago
.gitignore

24 Bytes

Ignore nohup output over 1 year ago
README.md

2.43 kB

Update ggml format model over 1 year ago
Whisper_finetuned_checkpoint_to_GGML.ipynb

95.1 kB

First trial over 1 year ago
added_tokens.json

2.08 kB

First trial over 1 year ago
all_results.json

344 Bytes

End of training over 1 year ago
config.json

1.01 kB

First trial over 1 year ago
eval_results.json

198 Bytes

End of training over 1 year ago
ggml-medium.eu.bin

1.53 GB
LFS

Update ggml format model over 1 year ago
merges.txt

494 kB

First trial over 1 year ago
normalizer.json

52.7 kB

First trial over 1 year ago
preprocessor_config.json

185 kB

First trial over 1 year ago
pytorch_model.bin
Detected Pickle imports (3)
- "torch.FloatStorage",
- "collections.OrderedDict",
- "torch._utils._rebuild_tensor_v2"
What is a pickle import?
3.06 GB
LFS

Training in progress, step 7000 over 1 year ago
run.sh

1.14 kB

Update the learning rate hyperparameter over 1 year ago
run_speech_recognition_seq2seq_streaming.py

26.2 kB

First trial over 1 year ago
special_tokens_map.json

2.08 kB

First trial over 1 year ago
tokenizer_config.json

843 Bytes

First trial over 1 year ago
train_results.json

167 Bytes

End of training over 1 year ago
trainer_state.json

35.9 kB

End of training over 1 year ago
training_args.bin
Detected Pickle imports (6)
- "transformers.training_args.OptimizerNames",
- "transformers.trainer_utils.HubStrategy",
- "transformers.trainer_utils.SchedulerType",
- "transformers.trainer_utils.IntervalStrategy",
- "torch.device",
- "transformers.training_args_seq2seq.Seq2SeqTrainingArguments"
How to fix it?
3.64 kB
LFS

Training in progress, step 1000 over 1 year ago
vocab.json

1.04 MB

First trial over 1 year ago

Detected Pickle imports (3)

Detected Pickle imports (6)