# speech-emotion-recognition-with-openai-whisper-large-v3 by Source: https://savrn.com/models/speech-emotion-recognition-with-openai-whisper-large-v3 Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve speech-emotion-recognition-with-openai-whisper-large-v3 (637M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 1.3 GB | 1.5 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.6 GB | 0.8 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.3 GB | 0.4 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the [SAVRN Index](https://savrn.com/ai-index/pricing/gpus), read Oct 23, 2026. [speech-emotion-recognition-with-openai-whisper-large-v3 on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/speech-emotion-recognition-with-openai-whisper-large-v3/gpus) ## Model Card By Muhammad Firdho, published under apache-2.0, revision 15fd07411456. ### Speech Emotion Recognition with Whisper This project leverages the Whisper model to recognize emotions in speech. The goal is to classify audio recordings into different emotional categories, such as Happy, Sad, Surprised, and etc. ### Dataset The dataset used for training and evaluation is sourced from multiple datasets, including: - [RAVDESS](https://zenodo.org/records/1188976#.XsAXemgzaUk) - [SAVEE](https://www.kaggle.com/datasets/ejlok1/surrey-audiovisual-expressed-emotion-savee/data) - [TESS](https://tspace.library.utoronto.ca/handle/1807/24487) - [URDU](https://www.kaggle.com/datasets/bitlord/urdu-language-speech-dataset) The dataset contains recordings labeled with various emotions. Below is the distribution of the emotions in the dataset: | Emotion | Count | |-------------|-----------| | sad | 752 | | happy | 752 | | angry | 752 | | neutral | 716 | | disgust | 652 | | fearful | 652 | | surprised | 652 | | calm | 192 | This distribution reflects the balance of emotions in the dataset, with some emotions having more samples than others. Excluded the "calm" emotion during training due to its underrepresentation. ### Preprocessing [Read the full model card (798 words)](https://savrn.com/models/speech-emotion-recognition-with-openai-whisper-large-v3/card) ## Configuration Architecture WhisperForAudioClassification Layers 32 Vocabulary size 51,866 Stored precision float32 Model type whisper ## Identity and Version Repository firdhokk/speech-emotion-recognition-with-openai-whisper-large-v3 Publisher Muhammad Firdho Task Audio classification Modality Audio Library transformers Parameters 637M parameters Languages Not stated by the source Revision 15fd0741145616b5b8c2a4549165674ea2252bb4 First published 2024-09-21 Last updated 2025-11-01 ## Files and Weights 6 files, 2.5 GB in total. The weights are 2 files totalling 2.5 GB in bin, safetensors. Weights2 files · 2.5 GB Configuration2 files · 1.9 KB Documentation1 file · 7.2 KB Repository1 file · 1.5 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 2.5 GB | d5a5dfcd9cf6 | | training_args.bin | Weights | 5.2 KB | 8684f29931ee | | config.json | Configuration | 1.6 KB | — | | preprocessor_config.json | Configuration | 340 B | — | | README.md | Documentation | 7.2 KB | — | | .gitattributes | Repository | 1.5 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 2.5 GB [Download from Muhammad Firdho](https://huggingface.co/firdhokk/speech-emotion-recognition-with-openai-whisper-large-v3) Released by Muhammad Firdho through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Derived from [openai/whisper-large-v3](https://savrn.com/models/whisper-large-v3) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 2.5 GB | | 16-bit | 1.3 GB | | 8-bit | 0.6 GB | | 4-bit | 0.3 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Questions About speech-emotion-recognition-with-openai-whisper-large-v3 ### How much GPU memory does speech-emotion-recognition-with-openai-whisper-large-v3 need? About 1.5 GB at 16-bit and 0.4 GB at 4-bit: the weights (637M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run speech-emotion-recognition-with-openai-whisper-large-v3 on? At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists. ### Can I use speech-emotion-recognition-with-openai-whisper-large-v3 commercially? Yes. speech-emotion-recognition-with-openai-whisper-large-v3 is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ## Similar Models Model · Audio classification ### [Qwen3-ForcedAligner-0.6B-4bit](https://savrn.com/models/qwen3-forcedaligner-0-6b-4bit) [Ivan](https://savrn.com/model-publishers/aufklarer) 4-bit quantized version of Qwen/Qwen3-ForcedAligner-0.6B for Apple Silicon inference via MLX. Predicts word-level timestamps for audio+text pairs in a single non-autoregressive forward pass. Unlike ASR (autoregressive, token-by-token), the forced aligner runs the entire sequence in one forward pass through the decoder. The classify head predicts a timestamp class (0–4999) at each token position, which maps to time via classindex × 80ms. This model is designed for use with speech-swift: Text decoder (attention projections, MLP, embeddings) quantized to 4-bit using group quantization (groupsize=64). Audio encoder and classify head kept as float16 for accuracy. Open weights apache-2.0 415M parameters mlx [View model](https://savrn.com/models/qwen3-forcedaligner-0-6b-4bit) Model · Audio classification ### [MuQ-large-msd-iter](https://savrn.com/models/muq-large-msd-iter) [MuQ](https://savrn.com/model-publishers/openmuq) This is the official repository for the paper "MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization". For more detailed information, we strongly recommend referring to https://github.com/tencent-ailab/MuQ and the paper). In this repo, the following models are released: - MuQ(see this link): A large music foundation model pre-trained via Self-Supervised Learning (SSL), achieving SOTA in various MIR tasks. - MuQ-MuLan(see this link): A music-text joint embedding model trained via contrastive learning, supporting both English and Chinese texts. To begin with, please use pip to install the official muq lib, and ensure that your python>=3.8: To extract music… Open weights cc-by-nc-4.0 333M parameters [View model](https://savrn.com/models/muq-large-msd-iter) Model · Audio classification ### [SER-Odyssey-Baseline-WavLM-Multi-Attributes](https://savrn.com/models/ser-odyssey-baseline-wavlm-multi-attributes) [Ali N. Salman](https://savrn.com/model-publishers/3loi) The model was trained on MSP-Podcast for the Odyssey 2024 Emotion Recognition competition baseline This particular model is the multi-attributed based model which predict arousal, dominance and valence in a range of approximately 0...1. CCC based on Test3 and Development sets of the Odyssey Competition Open weights mit 319M parameters transformers [View model](https://savrn.com/models/ser-odyssey-baseline-wavlm-multi-attributes) Model · Audio classification ### [wav2vec2-large-robust-24-ft-age-gender](https://savrn.com/models/wav2vec2-large-robust-24-ft-age-gender) [audEERING GmbH](https://savrn.com/model-publishers/audeering) The model expects a raw audio signal as input and outputs predictions for age in a range of approximately 0...1 (0...100 years) and gender expressing the probababilty for being child, female, or male. In addition, it also provides the pooled states of the last transformer layer. The model was created by fine-tuning Wav2Vec2-Large-Robust Timit and For this version of the model we trained all 24 transformer layers. An ONNX export of the model is available from Further details are given in the associated paper and tutorial. Open weights cc-by-nc-sa-4.0 318M parameters transformers [View model](https://savrn.com/models/wav2vec2-large-robust-24-ft-age-gender) Model · Audio classification ### [wavlm-emotion-russian-resd](https://savrn.com/models/wavlm-emotion-russian-resd) [Aniemore](https://savrn.com/model-publishers/aniemore) Speech emotion recognition for Russian over seven classes: anger, disgust, enthusiasm, fear, happiness, neutral, sadness. Fine-tuned from jonatasgrosman/expw2v2truwavlms363 on Aniemore/resd. Audio resampled to 16 kHz mono, clips capped at 12 s, normalized per utterance, padding masked. UA is macro-averaged recall, WA is accuracy, F1 is macro-averaged. All three test sets went through the same harness, so the rows are comparable to each other. The RESD split matches fold 1 of EmoBox bit for bit. The top entry there is WavLM-large at WA 56.47 / UA 55.87 / F1 55.82. These numbers are higher, but the training protocol differs — EmoBox freezes the encoder and trains a probe, this is a full… Open weights mit 317M parameters transformers [View model](https://savrn.com/models/wavlm-emotion-russian-resd) Model · Audio classification ### [wav2vec2-lg-xlsr-en-speech-emotion-recognition](https://savrn.com/models/wav2vec2-lg-xlsr-en-speech-emotion-recognition) [Enrique Hernández Calabrés](https://savrn.com/model-publishers/ehcalabres) The model is a fine-tuned version of jonatasgrosman/wav2vec2-large-xlsr-53-english for a Speech Emotion Recognition (SER) task. The dataset used to fine-tune the original pre-trained model is the RAVDESS dataset. This dataset provides 1440 samples of recordings from actors performing on 8 different emotions in English, which are: It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 4 - evalbatchsize: 4 - gradientaccumulationsteps: 2 - totaltrainbatchsize: 8 - lrschedulertype: linear - numepochs: 3 - mixedprecisiontraining: Native AMP Any doubt, contact me on Twitter. - Transformers 4.8.2… Open weights apache-2.0 316M parameters transformers [View model](https://savrn.com/models/wav2vec2-lg-xlsr-en-speech-emotion-recognition) ## Muhammad Firdho [All models and datasets](https://savrn.com/model-publishers/firdhokk) ## Versions - [15fd07411456](https://savrn.com/models/speech-emotion-recognition-with-openai-whisper-large-v3/versions/15fd07411456) · current 2026-09-18 ## Explore More - [All audio classification models](https://savrn.com/models/tasks/audio-classification) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-21. - [Hugging Face record](https://huggingface.co/firdhokk/speech-emotion-recognition-with-openai-whisper-large-v3) - [How the hub is built](https://savrn.com/model-hub/methodology)