update readme
Browse files
README.md
CHANGED
|
@@ -12,7 +12,9 @@ pipeline_tag: automatic-speech-recognition
|
|
| 12 |
- **Description:** This model is a fine-tuned version of the OpenAI Whisper Medium model, tailored for speech recognition tasks using the LEVI v2 dataset, which consists of classroom audiovisual recording data.
|
| 13 |
- **Model Architecture:** openai/whisper-medium
|
| 14 |
- **Dataset:** LEVI_LoFi_v2/TRAIN (per-utterance transcript and 16k WAV audio)
|
| 15 |
-
|
|
|
|
|
|
|
| 16 |
## Training Details
|
| 17 |
- **Training Procedure:**
|
| 18 |
- LoRA Parameter Efficient Fine-tuning technique with the following parameters:
|
|
|
|
| 12 |
- **Description:** This model is a fine-tuned version of the OpenAI Whisper Medium model, tailored for speech recognition tasks using the LEVI v2 dataset, which consists of classroom audiovisual recording data.
|
| 13 |
- **Model Architecture:** openai/whisper-medium
|
| 14 |
- **Dataset:** LEVI_LoFi_v2/TRAIN (per-utterance transcript and 16k WAV audio)
|
| 15 |
+
- both student and tutor speech were used
|
| 16 |
+
- manifest: LEVI_LoFi_v2_TRAIN_punc+cased.csv
|
| 17 |
+
-
|
| 18 |
## Training Details
|
| 19 |
- **Training Procedure:**
|
| 20 |
- LoRA Parameter Efficient Fine-tuning technique with the following parameters:
|