Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
awong-dev
/
whisper-large-v3-cantonese
like
0
Automatic Speech Recognition
TensorBoard
Safetensors
mozilla-foundation/common_voice_17_0
Yue Chinese
whisper
cantonese
License:
apache-2.0
Model card
Files
Files and versions
xet
Metrics
Training metrics
Community
Copy to bucket
new
main
whisper-large-v3-cantonese
59.9 GB
Ctrl+K
Ctrl+K
1 contributor
History:
6 commits
awong-dev
File-tuned on common voice 25 yue dataset. Full run with punctuation removed before CER calculation. LR 3e-6, 3 epochs, cosine schedule
b11baa4
verified
about 2 months ago
checkpoint-27000
File-tuned on common voice 25 yue dataset. Full run with punctuation removed before CER calculation. LR 3e-6, 3 epochs, cosine schedule
about 2 months ago
checkpoint-33000
File-tuned on common voice 25 yue dataset. Full run with punctuation removed before CER calculation. LR 3e-6, 3 epochs, cosine schedule
about 2 months ago
checkpoint-33012
File-tuned on common voice 25 yue dataset. Full run with punctuation removed before CER calculation. LR 3e-6, 3 epochs, cosine schedule
about 2 months ago
final
File-tuned on common voice 25 yue dataset. Full run with punctuation removed before CER calculation. LR 3e-6, 3 epochs, cosine schedule
about 2 months ago
runs
File-tuned on common voice 25 yue dataset. Full run with punctuation removed before CER calculation. LR 3e-6, 3 epochs, cosine schedule
about 2 months ago
.gitattributes
Safe
1.52 kB
initial commit
2 months ago
README.md
Safe
1.11 kB
File-tuned on common voice 25 yue dataset. Full run with punctuation removed before CER calculation. LR 3e-6, 3 epochs, cosine schedule
about 2 months ago
config.json
Safe
1.2 kB
Trained on common voice 22 yue using train.tsv as the validation dataset and the remainder of validated.tsv for training set
2 months ago
generation_config.json
Safe
4.04 kB
Trained on common voice 22 yue using train.tsv as the validation dataset and the remainder of validated.tsv for training set
2 months ago
model-00001-of-00002.safetensors
Safe
4.99 GB
xet
Trained on common voice 22 yue using 5% test, .5% eval and lr 3e-6
about 2 months ago
model-00002-of-00002.safetensors
Safe
1.18 GB
xet
Trained on common voice 22 yue using 5% test, .5% eval and lr 3e-6
about 2 months ago
model.safetensors.index.json
Safe
112 kB
Trained on common voice 22 yue using train.tsv as the validation dataset and the remainder of validated.tsv for training set
2 months ago
optimizer.pt
Safe
pickle
Detected Pickle imports (3)
"torch.FloatStorage"
,
"collections.OrderedDict"
,
"torch._utils._rebuild_tensor_v2"
What is a pickle import?
7.25 GB
xet
Trained on common voice 22 yue using 5% test, .5% eval and lr 3e-6
about 2 months ago
preprocessor_config.json
Safe
357 Bytes
Trained on common voice 22 yue using train.tsv as the validation dataset and the remainder of validated.tsv for training set
2 months ago
rng_state.pth
pickle
Detected Pickle imports (7)
"torch._utils._rebuild_tensor_v2"
,
"numpy._core.multiarray._reconstruct"
,
"numpy.dtype"
,
"collections.OrderedDict"
,
"numpy.ndarray"
,
"_codecs.encode"
,
"torch.ByteStorage"
How to fix it?
14.6 kB
xet
Trained on common voice 22 yue using 5% test, .5% eval and lr 3e-6
about 2 months ago
scheduler.pt
Safe
pickle
Pickle imports
No problematic imports detected
What is a pickle import?
1.47 kB
xet
Trained on common voice 22 yue using 5% test, .5% eval and lr 3e-6
about 2 months ago
trainer_state.json
Safe
42.7 kB
Trained on common voice 22 yue using 5% test, .5% eval and lr 3e-6
about 2 months ago
training_args.bin
pickle
Detected Pickle imports (10)
"transformers.training_args.OptimizerNames"
,
"transformers.trainer_utils.HubStrategy"
,
"transformers.training_args_seq2seq.Seq2SeqTrainingArguments"
,
"transformers.trainer_utils.IntervalStrategy"
,
"accelerate.utils.dataclasses.DistributedType"
,
"transformers.trainer_utils.SchedulerType"
,
"torch.device"
,
"accelerate.state.PartialState"
,
"transformers.trainer_utils.SaveStrategy"
,
"transformers.trainer_pt_utils.AcceleratorConfig"
How to fix it?
6.03 kB
xet
Trained on common voice 22 yue using 5% test, .5% eval and lr 3e-6
about 2 months ago