Hugging Face's logo

sjhuskey
/
enenlhet-whisper-model

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
whisper
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
sjhuskey commited on
Commit
8bb46c8
·
verified ·
1 Parent(s): c2ea3fc

Model save

Browse files
Files changed (7) hide show
  1. README.md +18 -2
  2. emissions.csv +2 -0
  3. model.safetensors +1 -1
  4. runs/Jul10_16-25-06_dd8486c7a8d9/events.out.tfevents.1752164723.dd8486c7a8d9.24621.1 +3 -0
  5. runs/Jul10_16-39-45_dd8486c7a8d9/events.out.tfevents.1752165655.dd8486c7a8d9.40072.0 +3 -0
  6. runs/Jul10_16-39-45_dd8486c7a8d9/events.out.tfevents.1752170515.dd8486c7a8d9.40072.1 +3 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -4,6 +4,8 @@ license: apache-2.0
4
  base_model: openai/whisper-small
5
  tags:
6
  - generated_from_trainer
 
 
7
  model-index:
8
  - name: enenlhet-whisper
9
  results: []
@@ -15,6 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
15
  # enenlhet-whisper
16
 
17
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
 
 
 
18
 
19
  ## Model description
20
 
@@ -39,10 +44,21 @@ The following hyperparameters were used during training:
39
  - seed: 42
40
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
  - lr_scheduler_type: linear
42
- - lr_scheduler_warmup_steps: 500
43
- - training_steps: 5000
44
  - mixed_precision_training: Native AMP
45
 
 
 
 
 
 
 
 
 
 
 
 
46
  ### Framework versions
47
 
48
  - Transformers 4.48.0
 
4
  base_model: openai/whisper-small
5
  tags:
6
  - generated_from_trainer
7
+ metrics:
8
+ - wer
9
  model-index:
10
  - name: enenlhet-whisper
11
  results: []
 
17
  # enenlhet-whisper
18
 
19
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 2.6704
22
+ - Wer: 350.3996
23
 
24
  ## Model description
25
 
 
44
  - seed: 42
45
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
  - lr_scheduler_type: linear
47
+ - lr_scheduler_warmup_steps: 200
48
+ - training_steps: 1000
49
  - mixed_precision_training: Native AMP
50
 
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
54
+ |:-------------:|:------:|:----:|:---------------:|:---------:|
55
+ | 3.4691 | 0.6349 | 200 | 3.4181 | 412.1878 |
56
+ | 2.8359 | 1.2698 | 400 | 2.9265 | 1983.0669 |
57
+ | 2.5813 | 1.9048 | 600 | 2.7429 | 869.3806 |
58
+ | 2.3921 | 2.5397 | 800 | 2.7003 | 761.1888 |
59
+ | 2.1266 | 3.1746 | 1000 | 2.6704 | 350.3996 |
60
+
61
+
62
  ### Framework versions
63
 
64
  - Transformers 4.48.0
emissions.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
2
+ 2025-07-10T17:54:15,codecarbon,29f11b05-f5e5-4696-b691-eee3be744aa8,5b0fa12a-3dd7-45bb-9766-cc326314d9f1,4398.062264288,0.09624162954250555,2.188273465884778e-05,42.5,52.081347793114205,38.0,0.05173205740056678,0.10682776796214602,0.04586902942283713,0.20442885478554992,Singapore,SGP,,,,Linux-6.1.123+-x86_64-with-glibc2.35,3.11.13,3.0.2,12,Intel(R) Xeon(R) CPU @ 2.20GHz,1,1 x NVIDIA A100-SXM4-40GB,103.8507,1.2872,83.4760627746582,machine,N,1.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88fd57dc14695e46faee4c527fbd37c4ad4418a5bd2d03d08a4c9f2854ce3e56
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aecd40ef8f58fed5b97f03b71d3fe989a5fb484aff603762c74ba85853c35e5d
3
  size 966995080
runs/Jul10_16-25-06_dd8486c7a8d9/events.out.tfevents.1752164723.dd8486c7a8d9.24621.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a32a4de35c0c107e652417fff317f412cb1974ab2346a9f18d4c3c38e47ad829
3
+ size 7089
runs/Jul10_16-39-45_dd8486c7a8d9/events.out.tfevents.1752165655.dd8486c7a8d9.40072.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3320f483bb7ea84250e568ef2c33954472acebae8ab63c6d76eb19b7e8fb8f6
3
+ size 17235
runs/Jul10_16-39-45_dd8486c7a8d9/events.out.tfevents.1752170515.dd8486c7a8d9.40072.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df100472e7d87c5795f16a6a08c72ba74d58eeeb33b0e8ddb1b6347109957efc
3
+ size 406
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e3eccfaffc94f6e67019907e5cedf718e6c9be474e127c58b1d05c532727df5
3
  size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6afc11505f01720f012673877c568b48dbac8966e126f892a3f50c970290760e
3
  size 5560