charris/whisper_tiny_lora_q_pro_j_proj
Browse files
README.md
CHANGED
|
@@ -5,6 +5,8 @@ tags:
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- audiofolder
|
|
|
|
|
|
|
| 8 |
base_model: openai/whisper-tiny
|
| 9 |
model-index:
|
| 10 |
- name: lora-whisper-tiny
|
|
@@ -17,6 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
# lora-whisper-tiny
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the audiofolder dataset.
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -45,6 +50,32 @@ The following hyperparameters were used during training:
|
|
| 45 |
- training_steps: 4000
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
### Framework versions
|
| 49 |
|
| 50 |
- PEFT 0.10.0
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- audiofolder
|
| 8 |
+
metrics:
|
| 9 |
+
- wer
|
| 10 |
base_model: openai/whisper-tiny
|
| 11 |
model-index:
|
| 12 |
- name: lora-whisper-tiny
|
|
|
|
| 19 |
# lora-whisper-tiny
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the audiofolder dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 1.1131
|
| 24 |
+
- Wer: 40.8556
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 50 |
- training_steps: 4000
|
| 51 |
- mixed_precision_training: Native AMP
|
| 52 |
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 57 |
+
| 1.8796 | 2.7 | 200 | 1.8730 | 46.8159 |
|
| 58 |
+
| 1.5505 | 5.41 | 400 | 1.5270 | 44.5912 |
|
| 59 |
+
| 1.2514 | 8.11 | 600 | 1.2960 | 44.1416 |
|
| 60 |
+
| 1.1319 | 10.81 | 800 | 1.1753 | 42.2831 |
|
| 61 |
+
| 1.1388 | 13.51 | 1000 | 1.1591 | 42.4407 |
|
| 62 |
+
| 1.1174 | 16.22 | 1200 | 1.1487 | 43.4789 |
|
| 63 |
+
| 1.1255 | 18.92 | 1400 | 1.1414 | 43.0061 |
|
| 64 |
+
| 1.102 | 21.62 | 1600 | 1.1358 | 42.5519 |
|
| 65 |
+
| 1.0848 | 24.32 | 1800 | 1.1310 | 42.8949 |
|
| 66 |
+
| 1.0912 | 27.03 | 2000 | 1.1272 | 41.1337 |
|
| 67 |
+
| 1.0894 | 29.73 | 2200 | 1.1240 | 41.6667 |
|
| 68 |
+
| 1.0697 | 32.43 | 2400 | 1.1216 | 42.5426 |
|
| 69 |
+
| 1.064 | 35.14 | 2600 | 1.1193 | 42.1348 |
|
| 70 |
+
| 1.0752 | 37.84 | 2800 | 1.1175 | 41.7825 |
|
| 71 |
+
| 1.0983 | 40.54 | 3000 | 1.1161 | 41.7037 |
|
| 72 |
+
| 1.0948 | 43.24 | 3200 | 1.1150 | 41.0641 |
|
| 73 |
+
| 1.0319 | 45.95 | 3400 | 1.1142 | 40.9807 |
|
| 74 |
+
| 1.0394 | 48.65 | 3600 | 1.1136 | 41.4303 |
|
| 75 |
+
| 1.0602 | 51.35 | 3800 | 1.1132 | 40.8695 |
|
| 76 |
+
| 1.0139 | 54.05 | 4000 | 1.1131 | 40.8556 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
### Framework versions
|
| 80 |
|
| 81 |
- PEFT 0.10.0
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1187136
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49f51ff1030a55771c45c54f70753407d4cfaef1a2cfbe8332c08b0d4a9f4b9e
|
| 3 |
size 1187136
|
runs/Apr02_22-06-55_37011883d813/events.out.tfevents.1712095622.37011883d813.1547.5
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d11ba95dd31f52c58ecf1f96cf76859db2a0d5bec1d6e7f03b0d7d592853108
|
| 3 |
+
size 45849
|