--- library_name: transformers license: apache-2.0 pipeline_tag: automatic-speech-recognition tags: - audio --- # Cascaded English Speech2Text Translation This is a pipeline for speech-to-text translation from English speech to any target language text based on the cascaded approach, that consists of ASR and translation. The pipeline employs [distil-whisper/distil-large-v3](https://huggingface.co/distil-whisper/distil-large-v3) for ASR (English speech -> English text) and [facebook/nllb-200-3.3B](https://huggingface.co/facebook/nllb-200-3.3B) for text translation. The input must be English speech, while the translation can be in any languages NLLB trained on. Please find the all available languages and their language codes [here](https://github.com/facebookresearch/flores/blob/main/flores200/README.md#languages-in-flores-200). **Model for Japanese speech translation is available at [ja-cascaded-s2t-translation](https://huggingface.co/japanese-asr/ja-cascaded-s2t-translation).** ## Benchmark The folloiwng table shows CER computed over the reference and predicted translation for translating English speech to Japanese text task (subsets of [CoVoST2 and Fleurs](https://huggingface.co/datasets/japanese-asr/en2ja.s2t_translation)) with different size of NLLB along with OpenAI Whisper models. | model | [CoVoST2 (En->Ja)](https://huggingface.co/datasets/japanese-asr/en2ja.s2t_translation)| [Fleurs (En->JA)](https://huggingface.co/datasets/japanese-asr/en2ja.s2t_translation) | |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------:|------------------------------------------------------------------------------------------------------:| | [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)) | 62.4 | 63.5 | | [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)) | 64.4 | 67.2 | | [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)) | 62.4 | 62.9 | | [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)) | 63.4 | 66.2 | | [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) | 178.9 | 209.5 | | [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) | 179.6 | 201.8 | | [openai/whisper-large](https://huggingface.co/openai/whisper-large) | 178.7 | 201.8 | | [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) | 178.7 | 202 | | [openai/whisper-small](https://huggingface.co/openai/whisper-small) | 178.9 | 206.8 | | [openai/whisper-base](https://huggingface.co/openai/whisper-base) | 179.5 | 214.2 | | [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) | 185.2 | 200.5 | See [https://github.com/kotoba-tech/kotoba-whisper](https://github.com/kotoba-tech/kotoba-whisper) for the evaluation detail. ### Inference Speed 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. Following table shows the mean inference time in second averaged over 10 trials on audio sample with different durations. | model | 10 | 30 | 60 | 300 | |:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|------:|------:|------:|------:| | [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 | | [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 | | [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 | | [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 | | [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) | 0.061 | 0.184 | 0.372 | 1.804 | | [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) | 0.062 | 0.199 | 0.415 | 1.854 | | [openai/whisper-large](https://huggingface.co/openai/whisper-large) | 0.062 | 0.183 | 0.363 | 1.899 | | [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) | 0.045 | 0.132 | 0.266 | 1.368 | | [openai/whisper-small](https://huggingface.co/openai/whisper-small) | 0.135 | 0.376 | 0.631 | 3.495 | | [openai/whisper-base](https://huggingface.co/openai/whisper-base) | 0.054 | 0.108 | 0.231 | 1.019 | | [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) | 0.045 | 0.124 | 0.208 | 0.838 | ## Usage Here is an example to translate English speech into Japanese text translation. First, download a sample speech. ```bash wget https://huggingface.co/datasets/japanese-asr/en_asr.esb_eval/resolve/main/sample.wav -O sample_en.wav ``` Then, run the pipeline as below. ```python3 from transformers import pipeline # load model pipe = pipeline( model="japanese-asr/en-cascaded-s2t-translation", model_translation="facebook/nllb-200-distilled-600M", tgt_lang="jpn_Jpan", model_kwargs={"attn_implementation": "sdpa"}, chunk_length_s=15, trust_remote_code=True, ) # translate output = pipe("./sample.wav") ``` Other NLLB models can be used by setting `model_translation` such as following. - [facebook/nllb-200-3.3B](https://huggingface.co/facebook/nllb-200-3.3B) - [facebook/nllb-200-distilled-600M](https://huggingface.co/facebook/nllb-200-distilled-600M) - [facebook/nllb-200-distilled-1.3B](https://huggingface.co/facebook/nllb-200-distilled-1.3B) - [facebook/nllb-200-1.3B](https://huggingface.co/facebook/nllb-200-1.3B)