Update README.md
Browse files
README.md
CHANGED
|
@@ -39,19 +39,19 @@ See [https://github.com/kotoba-tech/kotoba-whisper](https://github.com/kotoba-te
|
|
| 39 |
Due to the nature of cascaded approach, the pipeline has additional complexity compared to the single end2end OpenAI whisper models for the sake of high accuracy.
|
| 40 |
Following table shows the mean inference time in second averaged over 10 trials on audio sample with different durations.
|
| 41 |
|
| 42 |
-
| model | 10 | 30 | 60 |
|
| 43 |
-
|
| 44 |
-
| [japanese-asr/en-cascaded-s2t-translation](https://huggingface.co/japanese-asr/en-cascaded-s2t-translation) ([facebook/nllb-200-3.3B](https://huggingface.co/facebook/nllb-200-3.3B)) | 0.173 | 0.247 | 0.352 |
|
| 45 |
-
| [japanese-asr/en-cascaded-s2t-translation](https://huggingface.co/japanese-asr/en-cascaded-s2t-translation) ([facebook/nllb-200-1.3B](https://huggingface.co/facebook/nllb-200-1.3B)) | 0.173 | 0.24 | 0.348 |
|
| 46 |
-
| [japanese-asr/en-cascaded-s2t-translation](https://huggingface.co/japanese-asr/en-cascaded-s2t-translation) ([facebook/nllb-200-distilled-1.3B](https://huggingface.co/facebook/nllb-200-distilled-1.3B)) | 0.17 | 0.245 | 0.348 |
|
| 47 |
-
| [japanese-asr/en-cascaded-s2t-translation](https://huggingface.co/japanese-asr/en-cascaded-s2t-translation) ([facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M)) | 0.108 | 0.179 | 0.283 |
|
| 48 |
-
| [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) | 0.061 | 0.184 | 0.372 |
|
| 49 |
-
| [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) | 0.062 | 0.199 | 0.415 |
|
| 50 |
-
| [openai/whisper-large](https://huggingface.co/openai/whisper-large) | 0.062 | 0.183 | 0.363 |
|
| 51 |
-
| [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) | 0.045 | 0.132 | 0.266 |
|
| 52 |
-
| [openai/whisper-small](https://huggingface.co/openai/whisper-small) | 0.135 | 0.376 | 0.631 |
|
| 53 |
-
| [openai/whisper-base](https://huggingface.co/openai/whisper-base) | 0.054 | 0.108 | 0.231 |
|
| 54 |
-
| [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) | 0.045 | 0.124 | 0.208 |
|
| 55 |
|
| 56 |
## Usage
|
| 57 |
Here is an example to translate English speech into Japanese text translation.
|
|
|
|
| 39 |
Due to the nature of cascaded approach, the pipeline has additional complexity compared to the single end2end OpenAI whisper models for the sake of high accuracy.
|
| 40 |
Following table shows the mean inference time in second averaged over 10 trials on audio sample with different durations.
|
| 41 |
|
| 42 |
+
| model | 10 | 30 | 60 | 300 |
|
| 43 |
+
|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------:|------:|------:|------:|
|
| 44 |
+
| [japanese-asr/en-cascaded-s2t-translation](https://huggingface.co/japanese-asr/en-cascaded-s2t-translation) ([facebook/nllb-200-3.3B](https://huggingface.co/facebook/nllb-200-3.3B)) | 0.173 | 0.247 | 0.352 | 1.772 |
|
| 45 |
+
| [japanese-asr/en-cascaded-s2t-translation](https://huggingface.co/japanese-asr/en-cascaded-s2t-translation) ([facebook/nllb-200-1.3B](https://huggingface.co/facebook/nllb-200-1.3B)) | 0.173 | 0.24 | 0.348 | 1.515 |
|
| 46 |
+
| [japanese-asr/en-cascaded-s2t-translation](https://huggingface.co/japanese-asr/en-cascaded-s2t-translation) ([facebook/nllb-200-distilled-1.3B](https://huggingface.co/facebook/nllb-200-distilled-1.3B)) | 0.17 | 0.245 | 0.348 | 1.882 |
|
| 47 |
+
| [japanese-asr/en-cascaded-s2t-translation](https://huggingface.co/japanese-asr/en-cascaded-s2t-translation) ([facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M)) | 0.108 | 0.179 | 0.283 | 1.33 |
|
| 48 |
+
| [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) | 0.061 | 0.184 | 0.372 | 1.804 |
|
| 49 |
+
| [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) | 0.062 | 0.199 | 0.415 | 1.854 |
|
| 50 |
+
| [openai/whisper-large](https://huggingface.co/openai/whisper-large) | 0.062 | 0.183 | 0.363 | 1.899 |
|
| 51 |
+
| [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) | 0.045 | 0.132 | 0.266 | 1.368 |
|
| 52 |
+
| [openai/whisper-small](https://huggingface.co/openai/whisper-small) | 0.135 | 0.376 | 0.631 | 3.495 |
|
| 53 |
+
| [openai/whisper-base](https://huggingface.co/openai/whisper-base) | 0.054 | 0.108 | 0.231 | 1.019 |
|
| 54 |
+
| [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) | 0.045 | 0.124 | 0.208 | 0.838 |
|
| 55 |
|
| 56 |
## Usage
|
| 57 |
Here is an example to translate English speech into Japanese text translation.
|