Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,9 @@ datasets:
|
|
| 5 |
language:
|
| 6 |
- lv
|
| 7 |
pipeline_tag: automatic-speech-recognition
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
# General-purpose Latvian ASR model
|
|
@@ -13,6 +16,8 @@ This is a fine-tuned [whisper-large-v3](https://huggingface.co/openai/whisper-la
|
|
| 13 |
|
| 14 |
We also provide 4-bit, 5-bit and 8-bit quantized versions of the model in the GGML format for the use with [whisper.cpp](https://github.com/ggerganov/whisper.cpp).
|
| 15 |
|
|
|
|
|
|
|
| 16 |
## Training
|
| 17 |
|
| 18 |
Fine-tuning was done using the Hugging Face Transformers library with a modified [seq2seq script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/speech-recognition#sequence-to-sequence).
|
|
|
|
| 5 |
language:
|
| 6 |
- lv
|
| 7 |
pipeline_tag: automatic-speech-recognition
|
| 8 |
+
base_model:
|
| 9 |
+
- openai/whisper-large-v3
|
| 10 |
+
new_version: AiLab-IMCS-UL/whisper-large-v3-lv-late-cv19
|
| 11 |
---
|
| 12 |
|
| 13 |
# General-purpose Latvian ASR model
|
|
|
|
| 16 |
|
| 17 |
We also provide 4-bit, 5-bit and 8-bit quantized versions of the model in the GGML format for the use with [whisper.cpp](https://github.com/ggerganov/whisper.cpp).
|
| 18 |
|
| 19 |
+
**NB!** This model is superseded by a newer version: [whisper-large-v3-lv-late-cv19](https://huggingface.co/AiLab-IMCS-UL/whisper-large-v3-lv-late-cv19) model.
|
| 20 |
+
|
| 21 |
## Training
|
| 22 |
|
| 23 |
Fine-tuning was done using the Hugging Face Transformers library with a modified [seq2seq script](https://github.com/huggingface/transformers/tree/main/examples/pytorch/speech-recognition#sequence-to-sequence).
|