Sunbird

Sunflower-Gemma4-E2B

Deploy Dedicated

README

License: apache-2.0

Try it

▶ Open the Colab Demo Notebook

Supported Languages

Coverage varies considerably by language, roughly tracking the amount of training data available.

Translation & Speech Evaluation Covers: Acholi, Afrikaans, Akan, Alur, Amharic, Bambara, Bari, Bemba, Berber, Chichewa, Dagaare, Dagbani, Dinka, Ewe, French, Fulani, Hausa, Igbo, Ik, Ikposo, Jopadhola, Kabyle, Kakwa, Kalenjin, Kanuri, Karamojong, Kikuyu, Kinyarwanda, Kirundi, Kumam, Kupsabiny, Kwamba, Lango, Lendu, Lingala, Lubwisi, Luganda, Lugbara, Lugungu, Lugwere, Luhya, Lumasaba, Lunyole, Luo, Lusoga, Ma'di, Malagasy, Ndebele, Nigerian Pidgin, Oromo, Pokot, Rukiga, Rukonjo, Runyankole, Runyoro, Ruruuli, Rutooro, Samia, Shona, Somali, Sotho, Swahili, Tswana, Wolof, Xhosa, Yoruba, and Zulu.

Note: A language's presence in this list means it was evaluated; it does not imply equal quality across all languages. See evaluation metrics below for details on performance.

Inference

Sunflower-Gemma4-E2B follows standard Transformers patterns, but expects specific prompt formats for translation and speech transcription. Like Qwen, the base model supports a reasoning phase, but we recommend setting enable_thinking=False for standard translation tasks.

Text Translation

Translation expects a fixed instruction template: Translate from English to {language name}: {text}

python

messages = [    {"role": "system", "content": "You are Sunflower, a helpful assistant made by Sunbird AI who knows many African languages."},    {"role": "user", "content": "Translate from English to Luganda: Where is the nearest hospital?"}]

Tip: Use do_sample=False (greedy decoding) and temperature=0 for translation tasks.

Audio Transcription

The model was trained with prompts that explicitly name the spoken language. Convert audio to a 16 kHz mono waveform and keep it to 30 seconds or less.

python

messages = [    {"role": "system", "content": "You are Sunflower, a helpful assistant made by Sunbird AI who knows many African languages."},    {        "role": "user",        "content": [            {"type": "audio", "audio": audio_array}, # 16kHz mono numpy array            {"type": "text", "text": "Please transcribe this Luganda audio."},        ],    },]

vLLM (Text-Only Inference)

vLLM is highly recommended for fast deployments. Because this is a multimodal model, text-only vLLM setup requires disabling vision/audio inputs to save memory.

python

import osos.environ["VLLM_ENABLE_V1_MULTIPROCESSING"] = "0" from vllm import LLM, SamplingParamsfrom transformers import AutoProcessor MODEL_ID = "Sunbird/Sunflower-Gemma4-E2B" llm = LLM(    MODEL_ID,    dtype="bfloat16",    max_model_len=1024,    limit_mm_per_prompt={"image": 0, "audio": 0}, # Text-only mode    enforce_eager=True,)processor = AutoProcessor.from_pretrained(MODEL_ID) def make_prompt(text, target_lang):    messages = [        {"role": "system", "content": "You are Sunflower, a helpful assistant made by Sunbird AI who knows many African languages."},        {"role": "user", "content": f"Translate from English to {target_lang}: {text}"}    ]    return processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) sampling = SamplingParams(temperature=0.0, max_tokens=256) examples = [    ("Good morning, how are you?", "Luganda"),    ("The children are going to school today.", "Acholi"),    ("I would like to buy three kilograms of rice.", "Swahili"),]outputs = llm.generate([make_prompt(t, l) for t, l in examples], sampling)for (text, lang), out in zip(examples, outputs):    print(f"[{lang}] {text}\n     -> {out.outputs[0].text.strip()}\n")

Transformers (Multimodal / Audio)

python

import torchimport librosaimport numpy as npfrom transformers import AutoModelForMultimodalLM, AutoProcessor MODEL_ID = "Sunbird/Sunflower-Gemma4-E2B"dtype = torch.bfloat16 if torch.cuda.is_bf16_supported() else torch.float16 processor = AutoProcessor.from_pretrained(MODEL_ID)model = AutoModelForMultimodalLM.from_pretrained(    MODEL_ID, dtype=dtype, device_map="auto", attn_implementation="sdpa").eval() # Load Audioaudio, _ = librosa.load("audio.wav", sr=16_000, mono=True)audio = np.asarray(audio, dtype=np.float32)if len(audio) > 480_000:    raise ValueError("Please provide no more than 30 seconds of audio.") messages = [    {"role": "system", "content": "You are Sunflower, a helpful assistant made by Sunbird AI who knows many African languages."},    {"role": "user", "content": [        {"type": "audio", "audio": audio},        {"type": "text", "text": "Please transcribe this Luganda audio."}    ]}]prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) inputs = processor(    text=[prompt], audio=[audio], return_tensors="pt",    text_kwargs={"padding": False, "truncation": False, "add_special_tokens": False},    audio_kwargs={"max_length": 480_000}).to(model.device)inputs["input_features"] = inputs["input_features"].to(dtype=dtype) with torch.inference_mode():    output = model.generate(**inputs, max_new_tokens=256, do_sample=False) new_tokens = output[0][inputs["input_ids"].shape[-1]:]raw_response = processor.decode(new_tokens, skip_special_tokens=False)print(processor.parse_response(raw_response)["content"])

Training

The model was adapted via the following stages:

Continued pretraining on multilingual African-language text (documents, parallel text, transcripts, web, and synthetic text).
Speech SFT on audio-transcription examples.
Mixed text-and-audio SFT on translation, instruction, and speech-transcription tasks.
GRPO post-training to improve translation and general response quality using task-specific reward signals.

Evaluation

Text Translation

Translation quality measured as chrF on the Sunbird/salt69 test split (100 examples per language).

Table with columns: Languages, Directions, Macro BLEU, Macro chrF, Mean Length Ratio
Languages	Directions	Macro BLEU	Macro chrF	Mean Length Ratio
69	138	12.20	0.3413	1.06

Table with columns: Code, Language, EN→X BLEU, EN→X chrF, X→EN BLEU, X→EN chrF, Mean chrF
Code	Language	EN→X BLEU	EN→X chrF	X→EN BLEU	X→EN chrF	Mean chrF
afr	Afrikaans	57.68	0.7747	57.86	0.7649	0.7698
pcm	Nigerian Pidgin	32.76	0.6438	48.27	0.7306	0.6872

Speech Transcription

Reported ASR results span 110 dataset configurations from Sunbird/speech. Performance varies substantially by language and recording source.

Table with columns: Languages, Scored Examples, Macro Language WER, Macro Language CER, Macro Mean Utterance WER, Macro Mean Utterance CER
Languages	Scored Examples	Macro Language WER	Macro Language CER	Macro Mean Utterance WER	Macro Mean Utterance CER
51	5201	0.4720	0.1890	0.5110	0.2016

(Rates shown on a 0–1 scale; lower is better. WER can exceed 1.0 when insertions outnumber reference words.)

Table with columns: Code, Language, Scored, Corpus WER, Corpus CER
Code	Language	Scored	Corpus WER	Corpus CER
ach	Acholi	92	0.4086	0.1758
afr	Afrikaans	170	0.1413	0.0646
aka	Akan	50	0.4182	0.1779
amh

Limitations

Preview weights: Output will change before the stable release.
Uneven multilingual quality: Lower-resource languages have substantially lower automatic scores. The low-resource end of the table is genuinely weak, and output there should be verified by a speaker before use.
Translation variants: BLEU and chrF compare against a single reference and can penalize acceptable wording, dialect, or orthographic variants.
Speech variation: Accent, dialect, code-switching, background noise, and domain vocabulary can materially affect transcription.
Language prompting: The model was trained with language-specific transcription prompts and may perform poorly when the spoken language is omitted or named incorrectly.
Hallucinations: Like any LLM, it can produce fluent, confident, but incorrect translations or transcripts. This matters more in low-resource languages where errors are harder for non-speakers to spot.

License

Released under the Apache 2.0 license, matching the Gemma 4 base model.

Citation

bibtex

@misc{sunbird2026sunflowergemma4e2b,  title        = {Sunflower-Gemma4-E2B},  author       = {{Sunbird AI}},  year         = {2026},  howpublished = {\url{https://huggingface.co/Sunbird/Sunflower-Gemma4-E2B}},  note         = {Preview release: Multilingual text and speech model for African languages}}

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

Sunbird

Model Tree

Base

google/gemma-4-E2B-it

Fine-tuned

this model

Input Modalities

TextImage

Output Modalities

Text

Supported Functionality

Dedicated EndpointsContainer

Explore FriendliAI today

Get started Talk to an engineer

README

License: apache-2.0

Try it

▶ Open the Colab Demo Notebook

Supported Languages

Coverage varies considerably by language, roughly tracking the amount of training data available.

Note: A language's presence in this list means it was evaluated; it does not imply equal quality across all languages. See evaluation metrics below for details on performance.

Inference

Text Translation

Translation expects a fixed instruction template: Translate from English to {language name}: {text}

python

messages = [    {"role": "system", "content": "You are Sunflower, a helpful assistant made by Sunbird AI who knows many African languages."},    {"role": "user", "content": "Translate from English to Luganda: Where is the nearest hospital?"}]

messages = [    {"role": "system", "content": "You are Sunflower, a helpful assistant made by Sunbird AI who knows many African languages."},    {"role": "user", "content": "Translate from English to Luganda: Where is the nearest hospital?"}]

Tip: Use do_sample=False (greedy decoding) and temperature=0 for translation tasks.

Audio Transcription

The model was trained with prompts that explicitly name the spoken language. Convert audio to a 16 kHz mono waveform and keep it to 30 seconds or less.

python

messages = [    {"role": "system", "content": "You are Sunflower, a helpful assistant made by Sunbird AI who knows many African languages."},    {        "role": "user",        "content": [            {"type": "audio", "audio": audio_array}, # 16kHz mono numpy array            {"type": "text", "text": "Please transcribe this Luganda audio."},        ],    },]

messages = [    {"role": "system", "content": "You are Sunflower, a helpful assistant made by Sunbird AI who knows many African languages."},    {        "role": "user",        "content": [            {"type": "audio", "audio": audio_array}, # 16kHz mono numpy array            {"type": "text", "text": "Please transcribe this Luganda audio."},        ],    },]

vLLM (Text-Only Inference)

vLLM is highly recommended for fast deployments. Because this is a multimodal model, text-only vLLM setup requires disabling vision/audio inputs to save memory.

python

import osos.environ["VLLM_ENABLE_V1_MULTIPROCESSING"] = "0" from vllm import LLM, SamplingParamsfrom transformers import AutoProcessor MODEL_ID = "Sunbird/Sunflower-Gemma4-E2B" llm = LLM(    MODEL_ID,    dtype="bfloat16",    max_model_len=1024,    limit_mm_per_prompt={"image": 0, "audio": 0}, # Text-only mode    enforce_eager=True,)processor = AutoProcessor.from_pretrained(MODEL_ID) def make_prompt(text, target_lang):    messages = [        {"role": "system", "content": "You are Sunflower, a helpful assistant made by Sunbird AI who knows many African languages."},        {"role": "user", "content": f"Translate from English to {target_lang}: {text}"}    ]    return processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) sampling = SamplingParams(temperature=0.0, max_tokens=256) examples = [    ("Good morning, how are you?", "Luganda"),    ("The children are going to school today.", "Acholi"),    ("I would like to buy three kilograms of rice.", "Swahili"),]outputs = llm.generate([make_prompt(t, l) for t, l in examples], sampling)for (text, lang), out in zip(examples, outputs):    print(f"[{lang}] {text}\n     -> {out.outputs[0].text.strip()}\n")

import osos.environ["VLLM_ENABLE_V1_MULTIPROCESSING"] = "0" from vllm import LLM, SamplingParamsfrom transformers import AutoProcessor MODEL_ID = "Sunbird/Sunflower-Gemma4-E2B" llm = LLM(    MODEL_ID,    dtype="bfloat16",    max_model_len=1024,    limit_mm_per_prompt={"image": 0, "audio": 0}, # Text-only mode    enforce_eager=True,)processor = AutoProcessor.from_pretrained(MODEL_ID) def make_prompt(text, target_lang):    messages = [        {"role": "system", "content": "You are Sunflower, a helpful assistant made by Sunbird AI who knows many African languages."},        {"role": "user", "content": f"Translate from English to {target_lang}: {text}"}    ]    return processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) sampling = SamplingParams(temperature=0.0, max_tokens=256) examples = [    ("Good morning, how are you?", "Luganda"),    ("The children are going to school today.", "Acholi"),    ("I would like to buy three kilograms of rice.", "Swahili"),]outputs = llm.generate([make_prompt(t, l) for t, l in examples], sampling)for (text, lang), out in zip(examples, outputs):    print(f"[{lang}] {text}\n     -> {out.outputs[0].text.strip()}\n")

Transformers (Multimodal / Audio)

python

import torchimport librosaimport numpy as npfrom transformers import AutoModelForMultimodalLM, AutoProcessor MODEL_ID = "Sunbird/Sunflower-Gemma4-E2B"dtype = torch.bfloat16 if torch.cuda.is_bf16_supported() else torch.float16 processor = AutoProcessor.from_pretrained(MODEL_ID)model = AutoModelForMultimodalLM.from_pretrained(    MODEL_ID, dtype=dtype, device_map="auto", attn_implementation="sdpa").eval() # Load Audioaudio, _ = librosa.load("audio.wav", sr=16_000, mono=True)audio = np.asarray(audio, dtype=np.float32)if len(audio) > 480_000:    raise ValueError("Please provide no more than 30 seconds of audio.") messages = [    {"role": "system", "content": "You are Sunflower, a helpful assistant made by Sunbird AI who knows many African languages."},    {"role": "user", "content": [        {"type": "audio", "audio": audio},        {"type": "text", "text": "Please transcribe this Luganda audio."}    ]}]prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) inputs = processor(    text=[prompt], audio=[audio], return_tensors="pt",    text_kwargs={"padding": False, "truncation": False, "add_special_tokens": False},    audio_kwargs={"max_length": 480_000}).to(model.device)inputs["input_features"] = inputs["input_features"].to(dtype=dtype) with torch.inference_mode():    output = model.generate(**inputs, max_new_tokens=256, do_sample=False) new_tokens = output[0][inputs["input_ids"].shape[-1]:]raw_response = processor.decode(new_tokens, skip_special_tokens=False)print(processor.parse_response(raw_response)["content"])

import torchimport librosaimport numpy as npfrom transformers import AutoModelForMultimodalLM, AutoProcessor MODEL_ID = "Sunbird/Sunflower-Gemma4-E2B"dtype = torch.bfloat16 if torch.cuda.is_bf16_supported() else torch.float16 processor = AutoProcessor.from_pretrained(MODEL_ID)model = AutoModelForMultimodalLM.from_pretrained(    MODEL_ID, dtype=dtype, device_map="auto", attn_implementation="sdpa").eval() # Load Audioaudio, _ = librosa.load("audio.wav", sr=16_000, mono=True)audio = np.asarray(audio, dtype=np.float32)if len(audio) > 480_000:    raise ValueError("Please provide no more than 30 seconds of audio.") messages = [    {"role": "system", "content": "You are Sunflower, a helpful assistant made by Sunbird AI who knows many African languages."},    {"role": "user", "content": [        {"type": "audio", "audio": audio},        {"type": "text", "text": "Please transcribe this Luganda audio."}    ]}]prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) inputs = processor(    text=[prompt], audio=[audio], return_tensors="pt",    text_kwargs={"padding": False, "truncation": False, "add_special_tokens": False},    audio_kwargs={"max_length": 480_000}).to(model.device)inputs["input_features"] = inputs["input_features"].to(dtype=dtype) with torch.inference_mode():    output = model.generate(**inputs, max_new_tokens=256, do_sample=False) new_tokens = output[0][inputs["input_ids"].shape[-1]:]raw_response = processor.decode(new_tokens, skip_special_tokens=False)print(processor.parse_response(raw_response)["content"])

Training

The model was adapted via the following stages:

Continued pretraining on multilingual African-language text (documents, parallel text, transcripts, web, and synthetic text).
Speech SFT on audio-transcription examples.
Mixed text-and-audio SFT on translation, instruction, and speech-transcription tasks.
GRPO post-training to improve translation and general response quality using task-specific reward signals.

Evaluation

Text Translation

Translation quality measured as chrF on the Sunbird/salt69 test split (100 examples per language).

Table with columns: Languages, Directions, Macro BLEU, Macro chrF, Mean Length Ratio
Languages	Directions	Macro BLEU	Macro chrF	Mean Length Ratio
69	138	12.20	0.3413	1.06

Table with columns: Code, Language, EN→X BLEU, EN→X chrF, X→EN BLEU, X→EN chrF, Mean chrF
Code	Language	EN→X BLEU	EN→X chrF	X→EN BLEU	X→EN chrF	Mean chrF
afr	Afrikaans	57.68	0.7747	57.86	0.7649	0.7698
pcm	Nigerian Pidgin	32.76	0.6438	48.27	0.7306	0.6872

Speech Transcription

Reported ASR results span 110 dataset configurations from Sunbird/speech. Performance varies substantially by language and recording source.

Table with columns: Languages, Scored Examples, Macro Language WER, Macro Language CER, Macro Mean Utterance WER, Macro Mean Utterance CER
Languages	Scored Examples	Macro Language WER	Macro Language CER	Macro Mean Utterance WER	Macro Mean Utterance CER
51	5201	0.4720	0.1890	0.5110	0.2016

(Rates shown on a 0–1 scale; lower is better. WER can exceed 1.0 when insertions outnumber reference words.)

Table with columns: Code, Language, Scored, Corpus WER, Corpus CER
Code	Language	Scored	Corpus WER	Corpus CER
ach	Acholi	92	0.4086	0.1758
afr	Afrikaans	170	0.1413	0.0646
aka	Akan	50	0.4182	0.1779
amh

Limitations

Preview weights: Output will change before the stable release.
Uneven multilingual quality: Lower-resource languages have substantially lower automatic scores. The low-resource end of the table is genuinely weak, and output there should be verified by a speaker before use.
Translation variants: BLEU and chrF compare against a single reference and can penalize acceptable wording, dialect, or orthographic variants.
Speech variation: Accent, dialect, code-switching, background noise, and domain vocabulary can materially affect transcription.
Language prompting: The model was trained with language-specific transcription prompts and may perform poorly when the spoken language is omitted or named incorrectly.
Hallucinations: Like any LLM, it can produce fluent, confident, but incorrect translations or transcripts. This matters more in low-resource languages where errors are harder for non-speakers to spot.

License

Released under the Apache 2.0 license, matching the Gemma 4 base model.

Citation

bibtex

@misc{sunbird2026sunflowergemma4e2b,  title        = {Sunflower-Gemma4-E2B},  author       = {{Sunbird AI}},  year         = {2026},  howpublished = {\url{https://huggingface.co/Sunbird/Sunflower-Gemma4-E2B}},  note         = {Preview release: Multilingual text and speech model for African languages}}

@misc{sunbird2026sunflowergemma4e2b,  title        = {Sunflower-Gemma4-E2B},  author       = {{Sunbird AI}},  year         = {2026},  howpublished = {\url{https://huggingface.co/Sunbird/Sunflower-Gemma4-E2B}},  note         = {Preview release: Multilingual text and speech model for African languages}}