Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,7 @@ CHATWhisper is a series of ASR models specifically designed for the task for Lan
|
|
| 9 |
The models are based on `openai/whisper-large-v2` trained using an alpha=32, rank=16 LoRA. We will update the model card with evaluation performance shortly.
|
| 10 |
|
| 11 |
## Usage
|
| 12 |
-
The models can be used directly as a Whisper-class ASR model following the [same instructions](https://huggingface.co/openai/whisper-base) released by OpenAI. Alternatively, to get the full analysis possible with the model, it is best combined with the TalkBank Batchalign suite of analysis software, [available here](https://github.com/talkbank/
|
| 13 |
|
| 14 |
## Data
|
| 15 |
The models are trained with a combination of English Control Protocol samples from [the AphasiaBank corpus](https://aphasia.talkbank.org/) of conversational speech from three seperate corpora.
|
|
|
|
| 9 |
The models are based on `openai/whisper-large-v2` trained using an alpha=32, rank=16 LoRA. We will update the model card with evaluation performance shortly.
|
| 10 |
|
| 11 |
## Usage
|
| 12 |
+
The models can be used directly as a Whisper-class ASR model following the [same instructions](https://huggingface.co/openai/whisper-base) released by OpenAI. Alternatively, to get the full analysis possible with the model, it is best combined with the TalkBank Batchalign suite of analysis software, [available here](https://github.com/talkbank/batchalign2), using `transcribe` mode with the `--whisper` flag.
|
| 13 |
|
| 14 |
## Data
|
| 15 |
The models are trained with a combination of English Control Protocol samples from [the AphasiaBank corpus](https://aphasia.talkbank.org/) of conversational speech from three seperate corpora.
|