End of training
Browse files- README.md +8 -11
- model.safetensors +1 -1
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -25,18 +25,18 @@ model-index:
|
|
| 25 |
metrics:
|
| 26 |
- name: Wer
|
| 27 |
type: wer
|
| 28 |
-
value:
|
| 29 |
---
|
| 30 |
|
| 31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 32 |
should probably proofread and complete it, then remove this comment. -->
|
| 33 |
|
| 34 |
-
# Whisper Small Hi -
|
| 35 |
|
| 36 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 11.0 dataset.
|
| 37 |
It achieves the following results on the evaluation set:
|
| 38 |
-
- Loss:
|
| 39 |
-
- Wer:
|
| 40 |
|
| 41 |
## Model description
|
| 42 |
|
|
@@ -62,17 +62,14 @@ The following hyperparameters were used during training:
|
|
| 62 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 63 |
- lr_scheduler_type: linear
|
| 64 |
- lr_scheduler_warmup_steps: 10
|
| 65 |
-
- training_steps:
|
| 66 |
- mixed_precision_training: Native AMP
|
| 67 |
|
| 68 |
### Training results
|
| 69 |
|
| 70 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer
|
| 71 |
-
|:-------------:|:------:|:----:|:---------------:|:-------
|
| 72 |
-
|
|
| 73 |
-
| 1.5189 | 0.0183 | 30 | 1.5080 | 114.9920 |
|
| 74 |
-
| 1.3841 | 0.0275 | 45 | 1.3985 | 102.6115 |
|
| 75 |
-
| 1.3529 | 0.0367 | 60 | 1.3567 | 100.9015 |
|
| 76 |
|
| 77 |
|
| 78 |
### Framework versions
|
|
|
|
| 25 |
metrics:
|
| 26 |
- name: Wer
|
| 27 |
type: wer
|
| 28 |
+
value: 65.68187589943282
|
| 29 |
---
|
| 30 |
|
| 31 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 32 |
should probably proofread and complete it, then remove this comment. -->
|
| 33 |
|
| 34 |
+
# Whisper Small Hi - NoumidaA
|
| 35 |
|
| 36 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 11.0 dataset.
|
| 37 |
It achieves the following results on the evaluation set:
|
| 38 |
+
- Loss: 0.5952
|
| 39 |
+
- Wer: 65.6819
|
| 40 |
|
| 41 |
## Model description
|
| 42 |
|
|
|
|
| 62 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 63 |
- lr_scheduler_type: linear
|
| 64 |
- lr_scheduler_warmup_steps: 10
|
| 65 |
+
- training_steps: 1000
|
| 66 |
- mixed_precision_training: Native AMP
|
| 67 |
|
| 68 |
### Training results
|
| 69 |
|
| 70 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 71 |
+
|:-------------:|:------:|:----:|:---------------:|:-------:|
|
| 72 |
+
| 0.4581 | 0.6116 | 1000 | 0.5952 | 65.6819 |
|
|
|
|
|
|
|
|
|
|
| 73 |
|
| 74 |
|
| 75 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 151061672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb8e5897d6d417052a95e84533809ba6db80d202c66989ed088f81f5a1a80fe6
|
| 3 |
size 151061672
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5432
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75ecc9444717f31462875799b6c57200b37954424e867524dad52ba74a9219c0
|
| 3 |
size 5432
|