melvinrajendran
commited on
End of training
Browse files- README.md +8 -0
- config.json +1 -1
README.md
CHANGED
@@ -17,6 +17,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
# Whisper Tiny - CORAAL
|
18 |
|
19 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the AAVE Speech Recognition CORAAL dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
17 |
# Whisper Tiny - CORAAL
|
18 |
|
19 |
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the AAVE Speech Recognition CORAAL dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- eval_loss: 1.3805
|
22 |
+
- eval_model_preparation_time: 0.0026
|
23 |
+
- eval_wer: 44.7790
|
24 |
+
- eval_runtime: 24.5707
|
25 |
+
- eval_samples_per_second: 3.256
|
26 |
+
- eval_steps_per_second: 0.407
|
27 |
+
- step: 0
|
28 |
|
29 |
## Model description
|
30 |
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": false,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "melvinrajendran/whisper-tiny-coraal",
|
3 |
"activation_dropout": 0.0,
|
4 |
"activation_function": "gelu",
|
5 |
"apply_spec_augment": false,
|