SeamlessM4T

# SeamlessM4T v2 via Hugging Face transformers
pip install --upgrade transformers torch torchaudio

# infer.py
import torchaudio
from transformers import AutoProcessor, SeamlessM4Tv2Model

model_id  = "facebook/seamless-m4t-v2-large"
processor = AutoProcessor.from_pretrained(model_id)
model     = SeamlessM4Tv2Model.from_pretrained(model_id)

# ── Speech-to-text translation (S2TT) — English audio -> French text ──
audio, sr = torchaudio.load("meeting.wav")
audio = torchaudio.functional.resample(audio, sr, 16_000)
inputs = processor(audios=audio, return_tensors="pt")
text = model.generate(**inputs, tgt_lang="fra", generate_speech=False)
print(processor.decode(text[0].tolist()[0], skip_special_tokens=True))

# ── ASR (transcribe in source language) ──
asr = model.generate(**inputs, tgt_lang="eng", generate_speech=False)
print(processor.decode(asr[0].tolist()[0], skip_special_tokens=True))

# ── Speech-to-speech translation (S2ST) — returns a waveform ──
wav = model.generate(**inputs, tgt_lang="rus")[0].cpu().numpy().squeeze()

# fairseq2 source install · official Meta CLI
git clone https://github.com/facebookresearch/seamless_communication.git
cd seamless_communication

# fairseq2 wheel is published per torch / cuda; check the README for your combo
pip install -e .

# ── Speech-to-text translation: English wav -> French text ──
m4t_predict input.wav \
    --task s2tt \
    --src_lang eng \
    --tgt_lang fra \
    --model_name seamlessM4T_v2_large

# ── Speech-to-speech: English wav -> Spanish wav ──
m4t_predict input.wav \
    --task s2st \
    --src_lang eng \
    --tgt_lang spa \
    --model_name seamlessM4T_v2_large \
    --output_path translated.wav

# ── Text-to-text: French text -> English text ──
m4t_predict "Bonjour, comment ca va?" \
    --task t2tt \
    --src_lang fra \
    --tgt_lang eng \
    --model_name seamlessM4T_v2_large

# No code path — open in a browser:
#
#   https://huggingface.co/spaces/facebook/seamless_m4t
#
# The Space runs SeamlessM4T v2 with a UI for:
#   - S2ST  (mic / file -> translated audio)
#   - S2TT  (mic / file -> translated text)
#   - T2ST  (text -> translated audio)
#   - T2TT  (text -> translated text)
#
# Tip: the Space surface is rate-limited and occasionally offline
# while Meta rebuilds dependencies. If the demo errors, the next-best
# zero-install option is the companion notebook on the repo:
#   https://github.com/facebookresearch/seamless_communication/tree/main/demo