openai/whisper-base openai/whisper-small openai/whisper-medium openai/whisper-large openai/whisper-large-v2 openai/whisper-large-v3 欢迎大家扫码入知识星球(左)或者QQ群(右)讨论,知识星球里面提供项目的模型文件和博主其他相关项目的模型文件,也包括其他一些资源。
from_pretrained("openai/whisper-small", language="Hindi", task="transcribe") 我们可以通过对 Common Voice 数据集的第一个样本进行编解码来验证分词器是否正确编码了印地语字符。在对转录文本进行编码时,分词器在序列的开头和结尾添加“特殊标记”,其中包括文本的开始/结尾、语种标记和任务标记 (由上一...
whisper_size: 可选择 medium 和large 2.5 划分训练/测试集并标注 #@markdown 运行该单元格会生成划分好训练/测试集的最终标注,以及配置文件 #@markdown Running this block will generate final annotations for training & validation, as well as config file. #@markdown 选择是否加入辅助训练数据:/ Choose wh...
Whisperis a suite of ASR models, commonly accepted as the best performing models for the ASR task. It provides state-of-the-art performance for English ASR, while being well suited to multilingual fine-tuning from limited resources. However, when it comes to "resource-poor" languages such as...
We'll start our fine-tuning run from the pre-trained Whisper small checkpoint. To do this, we'll load the pre-trained weights from the Hugging Face Hub. Again, this is trivial through use of 🤗 Transformers! from transformers import WhisperForConditionalGeneration model = WhisperForC...
We'll start our fine-tuning run from the pre-trained Whisper small checkpoint. To do this, we'll load the pre-trained weights from the Hugging Face Hub. Again, this is trivial through use of 🤗 Transformers! from transformers import WhisperForConditionalGeneration model = Whispe...
下面,我们将以多语种版的 [`small`](https://huggingface.co/openai/whisper-small)checkpoint (参数量 244M (~= 1GB)) 为例,带大家走一遍微调模型的全过程。我们将使用 [Common Voice](https://huggingface.co/datasets/mozilla-foundation/common_voice_11_0) 数据集里的小语种数据来训练和评估我们的系统。
Good day i followed this blog post https://huggingface.co/blog/fine-tune-whisper, and used it with a Hausa dataset and the training was done successfully My issue now is that anytime run this command from transformers import WhisperForCo...
Whisper is a suite of ASR models, commonly accepted as the best performing models for the ASR task. It provides state-of-the-art performance for English ASR, while being well suited to multilingual fine-tuning from limited resources. However, when it comes to "resource-poor" langu...
whisper-small-np chevron_right folder checkpoint-17910empty folder checkpoint-7164empty folder runsempty Outputmore_vert arrow_drop_down folder whisper-small-np arrow_right folder checkpoint-17910 arrow_right folder checkpoint-7164 arrow_right folder runs Download notebook output navigate_nextminimize cont...