baileyarzate
commited on
Commit
•
6736912
1
Parent(s):
bc68b74
Update README.md
Browse files
README.md
CHANGED
@@ -1,13 +1,13 @@
|
|
1 |
---
|
2 |
-
library_name: transformers
|
3 |
-
tags: []
|
4 |
---
|
5 |
|
6 |
# Model Card for Model ID
|
7 |
|
8 |
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
|
10 |
-
|
11 |
|
12 |
## Model Details
|
13 |
|
@@ -15,8 +15,6 @@ tags: []
|
|
15 |
|
16 |
<!-- Provide a longer summary of what this model is. -->
|
17 |
|
18 |
-
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
19 |
-
|
20 |
- **Developed by:** Jesse Arzate
|
21 |
- **Model type:** Sequence-to-Sequence (Seq2Seq) Transformer-based model
|
22 |
- **Language(s) (NLP):** English
|
@@ -117,9 +115,6 @@ df_subset = pd.concat([df_subset, transcriptions_finetuned], axis=1)
|
|
117 |
Dataset: ATC audio recordings from actual flight operations.
|
118 |
Size: ~250 hours of annotated data.
|
119 |
|
120 |
-
|
121 |
-
[More Information Needed]
|
122 |
-
|
123 |
### Training Procedure
|
124 |
|
125 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
@@ -182,13 +177,11 @@ Randomly sampled 20% of the data with seed = 42.
|
|
182 |
|
183 |
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
184 |
|
185 |
-
Word Error Rate
|
186 |
-
Normalized Word Error Rate
|
187 |
|
188 |
### Results
|
189 |
|
190 |
-
Mean WER for 500 test samples: 0.145
|
191 |
-
with 95% confidence interval: (0.123, 0.167)
|
192 |
|
193 |
#### Summary
|
194 |
|
@@ -219,10 +212,10 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
219 |
|
220 |
#### Hardware
|
221 |
|
222 |
-
CPU
|
223 |
-
GPU
|
224 |
-
vRAM
|
225 |
-
RAM
|
226 |
|
227 |
#### Software
|
228 |
|
|
|
1 |
---
|
2 |
+
library_name: transformers, peft, torch
|
3 |
+
tags: [asr, whisper, finetune, atc, aircraft, communications, english]
|
4 |
---
|
5 |
|
6 |
# Model Card for Model ID
|
7 |
|
8 |
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
|
10 |
+
[SUMMARY HERE]
|
11 |
|
12 |
## Model Details
|
13 |
|
|
|
15 |
|
16 |
<!-- Provide a longer summary of what this model is. -->
|
17 |
|
|
|
|
|
18 |
- **Developed by:** Jesse Arzate
|
19 |
- **Model type:** Sequence-to-Sequence (Seq2Seq) Transformer-based model
|
20 |
- **Language(s) (NLP):** English
|
|
|
115 |
Dataset: ATC audio recordings from actual flight operations.
|
116 |
Size: ~250 hours of annotated data.
|
117 |
|
|
|
|
|
|
|
118 |
### Training Procedure
|
119 |
|
120 |
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
|
|
177 |
|
178 |
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
179 |
|
180 |
+
Word Error Rate, Normalized Word Error Rate
|
|
|
181 |
|
182 |
### Results
|
183 |
|
184 |
+
Mean WER for 500 test samples: 0.145 with 95% confidence interval: (0.123, 0.167)
|
|
|
185 |
|
186 |
#### Summary
|
187 |
|
|
|
212 |
|
213 |
#### Hardware
|
214 |
|
215 |
+
- **CPU**: AMD EPYC 7313P 16-Core Processor 3.00 GHz
|
216 |
+
- **GPU**: NVIDIA RTX A2000
|
217 |
+
- **vRAM**: 6GB
|
218 |
+
- **RAM**: 128GB
|
219 |
|
220 |
#### Software
|
221 |
|