BUD-E Whisper
is a suite of Whisper models fine-tuned for
direct emotional speech captioning
. The core models are built upon OpenAI's Whisper architecture, with the current primary variant being a fine-tune of
OpenAI Whisper Small
. These models are designed to generate text captions that not only transcribe speech but also inherently reflect its emotional content.
The embeddings generated by BUD-E Whisper can also serve as input for
Empathic Insight - Voice
, a downstream ensemble of Multi-Layer Perceptrons (MLPs) designed to predict dimensional emotion scores.
License
This model is released under the CC-by-4.0 license. Please give attribution to Maurice Kraus & Christoph Schuhmann, who made this model.
An
internal dataset
comprising approximately
5,000 hours of public Vlogs
and similar audio content.
Training Procedure & Caption Generation
A key aspect of BUD-E Whisper's development was a multi-step caption refinement process to create rich training targets:
Initial Score Generation:
An iterative process using Gemini Flash 2.0 generated initial 40-dimensional emotion scores (0-4 scale) and 15 additional dimensions like age, arousal, valence, dominance, harshness, vocalbursts,... for all audio snippets.
Templated Captions:
These scores were converted into templated string captions.
Paraphrasing for Richness:
Gemini Flash 2.0 was then used to paraphrase these templated captions, creating diverse and semantically rich training targets.
Fine-tuning:
Various Whisper model sizes (including the aforementioned fine-tune of OpenAI Whisper Small) were fine-tuned on these refined, emotionally-aware captions.
This multi-step caption refinement was crucial for performance. Direct score regression or simple templated captions were found to lead to suboptimal performance for emotional speech captioning with Whisper models.
Intended Use
Generating emotionally nuanced captions for audio content.
Providing rich embeddings for downstream emotion recognition tasks (e.g., with Empathic Insight - Voice).
Runs of laion BUD-E-Whisper on huggingface.co
6.0K
Total runs
254
24-hour runs
839
3-day runs
1.8K
7-day runs
5.0K
30-day runs
More Information About BUD-E-Whisper huggingface.co Model
BUD-E-Whisper huggingface.co is an AI model on huggingface.co that provides BUD-E-Whisper's model effect (), which can be used instantly with this laion BUD-E-Whisper model. huggingface.co supports a free trial of the BUD-E-Whisper model, and also provides paid use of the BUD-E-Whisper. Support call BUD-E-Whisper model through api, including Node.js, Python, http.
BUD-E-Whisper huggingface.co is an online trial and call api platform, which integrates BUD-E-Whisper's modeling effects, including api services, and provides a free online trial of BUD-E-Whisper, you can try BUD-E-Whisper online for free by clicking the link below.
laion BUD-E-Whisper online free url in huggingface.co:
BUD-E-Whisper is an open source model from GitHub that offers a free installation service, and any user can find BUD-E-Whisper on GitHub to install. At the same time, huggingface.co provides the effect of BUD-E-Whisper install, users can directly use BUD-E-Whisper installed effect in huggingface.co for debugging and trial. It also supports api for free installation.