From abe42609dd7f7ac39d82573a7c91cf223ff2fe98 Mon Sep 17 00:00:00 2001 From: Merve Noyan Date: Sat, 31 Aug 2024 23:06:50 +0300 Subject: [PATCH] Address VB's comments --- packages/tasks/src/tasks/audio-classification/data.ts | 4 ++-- packages/tasks/src/tasks/automatic-speech-recognition/data.ts | 2 +- packages/tasks/src/tasks/text-to-speech/data.ts | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/packages/tasks/src/tasks/audio-classification/data.ts b/packages/tasks/src/tasks/audio-classification/data.ts index 5aa5fa303..be123d341 100644 --- a/packages/tasks/src/tasks/audio-classification/data.ts +++ b/packages/tasks/src/tasks/audio-classification/data.ts @@ -63,7 +63,7 @@ const taskData: TaskDataCustom = { }, { description: "A language identification model.", - id: "speechbrain/lang-id-voxlingua107-ecapa", + id: "facebook/mms-lid-126", }, ], spaces: [ @@ -74,7 +74,7 @@ const taskData: TaskDataCustom = { ], summary: "Audio classification is the task of assigning a label or class to a given audio. It can be used for recognizing which command a user is giving or the emotion of a statement, as well as identifying a speaker.", - widgetModels: ["speechbrain/lang-id-voxlingua107-ecapa"], + widgetModels: ["MIT/ast-finetuned-audioset-10-10-0.4593"], youtubeId: "KWwzcmG98Ds", }; diff --git a/packages/tasks/src/tasks/automatic-speech-recognition/data.ts b/packages/tasks/src/tasks/automatic-speech-recognition/data.ts index 403abdd3f..000b3ea12 100644 --- a/packages/tasks/src/tasks/automatic-speech-recognition/data.ts +++ b/packages/tasks/src/tasks/automatic-speech-recognition/data.ts @@ -8,7 +8,7 @@ const taskData: TaskDataCustom = { }, { description: "An English dataset with 1,000 hours of data.", - id: "openslr/librispeech_asr", + id: "parler-tts/mls_eng", }, { description: "A multi-lingual audio dataset with 370K hours of audio.", diff --git a/packages/tasks/src/tasks/text-to-speech/data.ts b/packages/tasks/src/tasks/text-to-speech/data.ts index 3b0092cfa..22bd1202d 100644 --- a/packages/tasks/src/tasks/text-to-speech/data.ts +++ b/packages/tasks/src/tasks/text-to-speech/data.ts @@ -36,7 +36,7 @@ const taskData: TaskDataCustom = { models: [ { description: "A powerful TTS model.", - id: "suno/bark", + id: "parler-tts/parler-tts-large-v1", }, { description: "A massively multi-lingual TTS model.",