Update README.md
Browse files
README.md
CHANGED
@@ -26,14 +26,10 @@ This model is a fine-tuned version of [facebook/bart-large-cnn](https://huggingf
|
|
26 |
|
27 |
The model was developed for the project [HealthScirbe](https://github.com/hari-krishnan-88/HealthScribe-Clinical_Note_Generator). This model is integrated with a Flask web application. The project is a web application that allows users to generate clinical notes from transcribed ASR(Automatic Speech Recognition) data of conversations between doctors and patients.
|
28 |
|
29 |
-
|
30 |
-
|
31 |
-
The model is used to generate clinical notes from doctor-patient conversation data(ASR). This model has certain limitations like :
|
32 |
-
- N/A output generation is low. Sometimes None is produced
|
33 |
-
- When the input data is composed of very minimal character tokens or if input is very large it starts to hallucinate.
|
34 |
|
|
|
35 |
|
36 |
-
### TEST DATA Sample For Inference (More given in [`test.txt`](https://huggingface.co/har1/HealthScribe-Clinical_Note_Generator/blob/main/test.txt))
|
37 |
```
|
38 |
"Doctor: Hi there, I love that dress, very pretty!
|
39 |
Patient: Thank you for complementing a seventy-two-year-old patient.
|
@@ -51,6 +47,16 @@ Doctor: Great.
|
|
51 |
Patient: Yeah."
|
52 |
```
|
53 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
## Training and evaluation data
|
55 |
|
56 |
The model achieves the following results on the evaluation set:
|
|
|
26 |
|
27 |
The model was developed for the project [HealthScirbe](https://github.com/hari-krishnan-88/HealthScribe-Clinical_Note_Generator). This model is integrated with a Flask web application. The project is a web application that allows users to generate clinical notes from transcribed ASR(Automatic Speech Recognition) data of conversations between doctors and patients.
|
28 |
|
29 |
+
### TEST DATA Sample For Inference (More given in [`test.txt`](https://huggingface.co/har1/HealthScribe-Clinical_Note_Generator/blob/main/test.txt))
|
|
|
|
|
|
|
|
|
30 |
|
31 |
+
You can refer [`test.txt`](https://huggingface.co/har1/HealthScribe-Clinical_Note_Generator/blob/main/test.txt) for further examples of conversations.
|
32 |
|
|
|
33 |
```
|
34 |
"Doctor: Hi there, I love that dress, very pretty!
|
35 |
Patient: Thank you for complementing a seventy-two-year-old patient.
|
|
|
47 |
Patient: Yeah."
|
48 |
```
|
49 |
|
50 |
+
|
51 |
+
## Intended uses & limitations
|
52 |
+
|
53 |
+
The model is used to generate clinical notes from doctor-patient conversation data(ASR). This model has certain limitations like :
|
54 |
+
- N/A output generation is low. Sometimes None is produced
|
55 |
+
- When the input data is composed of very minimal character tokens or if input is very large it starts to hallucinate.
|
56 |
+
|
57 |
+
|
58 |
+
# Training Metrics
|
59 |
+
|
60 |
## Training and evaluation data
|
61 |
|
62 |
The model achieves the following results on the evaluation set:
|