# ddlBoJack/emotion2vec

[ACL 2024] Official PyTorch code for extracting features and training downstream models with emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation

Repository: https://github.com/ddlBoJack/emotion2vec
Canonical: https://ross.abutalabs.com/products/emotion2vec
Language: Python
License Family: other
Topics: iemocap, pytorch-implementation, speech-emotion-recognition, speech-representation
Last push: 2024-12-23T06:54:27+00:00

## Health v2 (maintenance only)
Score: 27/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 72
- inputs: {"age_days": 1012, "days_push": 618, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1179, forks 89 (observed 2026-08-28T04:03:53.127745+00:00)

## What it is
Official PyTorch implementation of emotion2vec, a self-supervised pre-trained model for speech emotion representation. It provides code for extracting emotion features from speech and training downstream speech emotion recognition models, with pretrained checkpoints available via ModelScope, Hugging Face, and FunASR.

## Use cases
- extract emotion embeddings from speech audio
- train a speech emotion recognition classifier
- fine-tune a pretrained emotion recognition model on my dataset
- recognize 9-class emotions from audio recordings
- get speech emotion features for downstream tasks
- run emotion2vec through FunASR or ModelScope

## When to choose
- you need state-of-the-art speech emotion recognition features or models
- you want a self-supervised speech emotion encoder to fine-tune
- you work with IEMOCAP-style SER benchmarks or research
- you prefer loading models through FunASR, ModelScope, or Hugging Face

## When to avoid
- you need general speech recognition (ASR) rather than emotion analysis
- you need a production service with a REST API out of the box
- you require a permissive license guarantee - the repo has no explicit license file
- you need non-Linux platform support or Windows-specific tooling

## Facets
- artifact type: library
- maturity: active
- function: speech-recognition, machine-learning, audio-processing, nlp
- domain: speech-processing, machine-learning, deep-learning
- platform: python
- tags: speech-emotion-recognition, self-supervised-learning, pytorch, pretrained-models, feature-extraction, funasr, iemocap, research-code, audio, linux

## Member repositories
- ddlBoJack/emotion2vec (main) score 27

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:53.127745+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:25:34.074963+00:00, confidence not recorded.
  - readme: https://github.com/ddlBoJack/emotion2vec (fetched 2026-08-28T04:03:53.127745+00:00, sha 79164845c1b7)
- Data as of 2026-08-30T08:39:29.467469+00:00.