Hugging Face's logo

ptotheun
/
whisper-tiny-th

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
ptotheun commited on
Commit
4ff06d2
·
verified ·
1 Parent(s): 9fc28a5

./whisper-tiny-th

Browse files
Files changed (5) hide show
  1. README.md +8 -8
  2. model.safetensors +1 -1
  3. runs/Sep14_15-45-14_c42f29339f68/events.out.tfevents.1726328725.c42f29339f68.2188.0 +3 -0
  4. runs/Sep14_15-45-14_c42f29339f68/events.out.tfevents.1726330448.c42f29339f68.2188.1 +3 -0
  5. training_args.bin +1 -1
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.8860
20
- - Cer: 35.4839
21
 
22
  ## Model description
23
 
@@ -48,16 +48,16 @@ The following hyperparameters were used during training:
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Cer |
50
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
51
- | No log | 1.0 | 7 | 0.9718 | 37.0968 |
52
- | 1.1407 | 2.0 | 14 | 0.9296 | 55.2419 |
53
- | 0.895 | 3.0 | 21 | 0.9023 | 53.9315 |
54
- | 0.895 | 4.0 | 28 | 0.8905 | 33.4677 |
55
- | 0.8158 | 5.0 | 35 | 0.8860 | 35.4839 |
56
 
57
 
58
  ### Framework versions
59
 
60
  - Transformers 4.44.2
61
  - Pytorch 2.4.0+cu121
62
- - Datasets 2.21.0
63
  - Tokenizers 0.19.1
 
16
 
17
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.8797
20
+ - Cer: 32.5605
21
 
22
  ## Model description
23
 
 
48
 
49
  | Training Loss | Epoch | Step | Validation Loss | Cer |
50
  |:-------------:|:-----:|:----:|:---------------:|:-------:|
51
+ | 0.0985 | 1.0 | 44 | 0.7953 | 32.9637 |
52
+ | 0.0465 | 2.0 | 88 | 0.8320 | 31.4516 |
53
+ | 0.0274 | 3.0 | 132 | 0.8624 | 33.2661 |
54
+ | 0.0178 | 4.0 | 176 | 0.8752 | 32.5605 |
55
+ | 0.0165 | 5.0 | 220 | 0.8797 | 32.5605 |
56
 
57
 
58
  ### Framework versions
59
 
60
  - Transformers 4.44.2
61
  - Pytorch 2.4.0+cu121
62
+ - Datasets 3.0.0
63
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9eb7edeaa5c7e7c3802a247eb057c7fc34ea17082f72db3baecb593ec2df0ed
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2c488ac18b63f29a98314017fdc3b89030b8140d9e383ec4044bf1860121ba5
3
  size 151061672
runs/Sep14_15-45-14_c42f29339f68/events.out.tfevents.1726328725.c42f29339f68.2188.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6af898082334e00d6bb5828852d4ac90963df1fea30083dab503dd5fc2391e7
3
+ size 13209
runs/Sep14_15-45-14_c42f29339f68/events.out.tfevents.1726330448.c42f29339f68.2188.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3ee0a6dade62c8a66dd95b416122366526123f93a99a7a762abec0376886ea3
3
+ size 13209
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:935595f26a994f7f099c7d0ad05db47fd60294a0d9dd6c414624ad530e7039ab
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a82b125a4dec72b82b291521441d9ceb528bf0118b1470615d38902511cda01c
3
  size 5368