From 7459bf8ad0c576d1637da7dd5fec3ca99635950f Mon Sep 17 00:00:00 2001 From: Felippe Chemello Date: Wed, 11 Jan 2023 12:11:41 -0300 Subject: [PATCH] Add PT (pt-br) align support --- README.md | 2 +- whisperx/transcribe.py | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 6af17b3..3afd7c7 100644 --- a/README.md +++ b/README.md @@ -93,7 +93,7 @@ https://user-images.githubusercontent.com/36994049/207743923-b4f0d537-29ae-4be2- The phoneme ASR alignment model is *language-specific*, for tested languages these models are [automatically picked from torchaudio pipelines or huggingface](https://github.com/m-bain/whisperX/blob/e909f2f766b23b2000f2d95df41f9b844ac53e49/whisperx/transcribe.py#L22). Just pass in the `--language` code, and use the whisper `--model large`. -Currently default models provided for `{en, fr, de, es, it, ja, zh, nl, uk}`. If the detected language is not in this list, you need to find a phoneme-based ASR model from [huggingface model hub](https://huggingface.co/models) and test it on your data. +Currently default models provided for `{en, fr, de, es, it, ja, zh, nl, uk, pt}`. If the detected language is not in this list, you need to find a phoneme-based ASR model from [huggingface model hub](https://huggingface.co/models) and test it on your data. #### E.g. German diff --git a/whisperx/transcribe.py b/whisperx/transcribe.py index 85bcda5..62e96f2 100644 --- a/whisperx/transcribe.py +++ b/whisperx/transcribe.py @@ -32,6 +32,7 @@ DEFAULT_ALIGN_MODELS_HF = { "zh": "jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn", "nl": "jonatasgrosman/wav2vec2-large-xlsr-53-dutch", "uk": "Yehor/wav2vec2-xls-r-300m-uk-with-small-lm", + "pt": "joaoalvarenga/wav2vec2-large-100k-voxpopuli-pt" }