 ai.google.dev'de görüntüle
|
 Google Colab'de çalıştırma
|
 Kaggle'da çalıştırma
|
 Vertex AI'da aç
|
 Kaynağı GitHub'da görüntüleyin
|
Gemma 3n'den itibaren, sesleri doğrudan istemlerinizde ve iş akışlarınızda kullanabilirsiniz. Ses ve konuşma dili, kullanıcı amaçlarını yakalamak, etrafımızdaki dünya hakkında bilgi kaydetmek ve çözülmesi gereken belirli sorunları anlamak için zengin veri kaynaklarıdır.
Bu kılavuzda, otomatik konuşma tanıma (ASR), çeviri ve genel konuşma anlama dahil olmak üzere Gemma 4'ün ses işleme özelliklerine genel bir bakış sunulmaktadır.
Bu not defteri T4 GPU'da çalışır.
Python paketlerini yükleme
Gemma modelini çalıştırmak ve istekte bulunmak için gereken Hugging Face kitaplıklarını yükleyin.
# Install PyTorch & other librariespip install torch accelerate# Install the transformers librarypip install transformers
Modeli Yükle
Aşağıdaki kod örneğinde gösterildiği gibi transformers kitaplıklarını kullanarak AutoProcessor ve AutoModelForImageTextToText sınıflarını kullanarak processor ve model örneği oluşturun:
MODEL_ID = "google/gemma-4-E2B-it" # @param ["google/gemma-4-E2B-it","google/gemma-4-E4B-it", "google/gemma-4-31B-it", "google/gemma-4-26B-A4B-it"]
from transformers import AutoProcessor, AutoModelForMultimodalLM
model = AutoModelForMultimodalLM.from_pretrained(MODEL_ID, dtype="auto", device_map="auto")
processor = AutoProcessor.from_pretrained(MODEL_ID)
Loading weights: 0%| | 0/2011 [00:00<?, ?it/s]
Ses verileri
Dijital ses verileri birçok biçimde ve çözünürlük düzeyinde olabilir. Gemma ile kullanabileceğiniz gerçek ses biçimleri (ör. MP3 ve WAV biçimleri), ses verilerini tensörlere dönüştürmek için seçtiğiniz çerçeveye göre belirlenir. Gemma ile işlenmek üzere ses verilerini hazırlarken dikkate almanız gereken bazı özel noktaları aşağıda bulabilirsiniz:
- Jeton maliyeti: Gemma 4 için her saniyelik ses 25 jeton değerindedir. (Gemma 3n için 6,25 jeton)
- Klip uzunluğu: Ses, maksimum 30 saniye uzunluğu destekler.
- Ses kanalları: Ses verileri tek bir ses kanalı olarak işlenir. Sol ve sağ kanallar gibi çok kanallı ses kullanıyorsanız kanalları kaldırarak veya ses verilerini tek bir kanalda birleştirerek verileri tek bir kanala indirgemeyi düşünebilirsiniz.
- Teknik Kodlama:
- Örnekleme hızı: 32 ms'lik kareler kullanılarak 16 kHz.
- Bit Derinliği: 32 bit kayan nokta biçimi, örnekler [-1, 1] aralığında normalleştirilir.
İşlemeyi planladığınız ses verileri, özellikle kanal sayısı, örnekleme hızı ve bit derinliği açısından giriş işleminden önemli ölçüde farklıysa ses verilerinizi yeniden örnekleyerek veya kırparak modelin işlediği veri çözünürlüğüne uygun hale getirmeyi düşünebilirsiniz.
Ses kodlama
Üst düzey kitaplıklar (ör. Hugging Face AutoProcessor) genellikle ses ön işlemesini otomatik olarak yapsa da bazen özel kodlama uygulamanız gerekebilir.
Gemma ile kullanılmak üzere kendi kod uygulamanızla ses verilerini kodlarken önerilen dönüştürme sürecini izlemeniz gerekir. MP3 veya WAV kodlu veriler gibi belirli bir biçimde kodlanmış ses dosyalarıyla çalışıyorsanız bunları önce ffmpeg gibi bir kitaplık kullanarak örneklere kod çözmeniz gerekir. Veriler kod çözüldükten sonra sesi, [-1, 1] aralığında tek kanallı, 16 kHz float32 dalga biçimlerine dönüştürün. Örneğin, 44, 1 kHz'de stereo imzalı 16 bit PCM tamsayı WAV dosyalarıyla çalışıyorsanız aşağıdaki adımları uygulayın:
- Ses verilerini 16 kHz'ye yeniden örnekleyin.
- 2 kanalı ortalayarak stereo sesin mono sese dönüştürülmesi
- int16'dan float32'ye dönüştürün ve [-1, 1] aralığına ölçeklemek için 32768, 0'a bölün.
Sesle yazma
Gemma 4 E2B ve E4B, çok dilli konuşma tanıma için eğitilmiştir. Bu sayede, çeşitli dillerdeki ses girişlerini metne dönüştürebilirsiniz. Aşağıdaki kod örneklerinde, Hugging Face Transformers'ı kullanarak modelden ses dosyalarındaki metinleri transkribe etmesini isteme yöntemi gösterilmektedir:
RESOURCE_URL_PREFIX = "https://raw.githubusercontent.com/google-gemma/cookbook/refs/heads/main/Demos/sample-data/"
messages = [
{
"role": "user",
"content": [
{"type": "text", "text": "Transcribe the following speech segment in its original language. Follow these specific instructions for formatting the answer:\n* Only output the transcription, with no newlines.\n* When transcribing numbers, write the digits, i.e. write 1.7 and not one point seven, and write 3 instead of three."},
#{"type": "text", "text": "Transcribe the following speech segment in English into English text. Follow these specific instructions for formatting the answer:\n* Only output the transcription, with no newlines.\n* When transcribing numbers, write the digits, i.e. write 1.7 and not one point seven, and write 3 instead of three."},
{"type": "audio", "audio": f"{RESOURCE_URL_PREFIX}journal1.wav"},
]
}
]
input_ids = processor.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True, return_dict=True,
return_tensors="pt",
)
input_ids = input_ids.to(model.device, dtype=model.dtype)
outputs = model.generate(**input_ids, max_new_tokens=64)
text = processor.batch_decode(
outputs,
skip_special_tokens=False,
clean_up_tokenization_spaces=False
)
print(text[0])
<bos><|turn>user Transcribe the following speech segment in its original language. Follow these specific instructions for formatting the answer: * Only output the transcription, with no newlines. * When transcribing numbers, write the digits, i.e. write 1.7 and not one point seven, and write 3 instead of three.<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|><turn|> <|turn>model I woke up early today feeling really fresh the morning light was beautiful and I enjoyed a nice cup of coffee<turn|>
messages = [
{
"role": "user",
"content": [
{"type": "text", "text": "Give me a concise overview of these audio files."},
{"type": "text", "text": "journal1:"},
{"type": "audio", "audio": f"{RESOURCE_URL_PREFIX}journal1.wav"},
{"type": "text", "text": "journal2:"},
{"type": "audio", "audio": f"{RESOURCE_URL_PREFIX}journal2.wav"},
{"type": "text", "text": "journal3:"},
{"type": "audio", "audio": f"{RESOURCE_URL_PREFIX}journal3.wav"},
{"type": "text", "text": "journal4:"},
{"type": "audio", "audio": f"{RESOURCE_URL_PREFIX}journal4.wav"},
{"type": "text", "text": "journal5:"},
{"type": "audio", "audio": f"{RESOURCE_URL_PREFIX}journal5.wav"},
]
}
]
input_ids = processor.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True, return_dict=True,
return_tensors="pt",
)
input_ids = input_ids.to(model.device, dtype=model.dtype)
outputs = model.generate(**input_ids, max_new_tokens=1024)
text = processor.batch_decode(
outputs,
skip_special_tokens=False,
clean_up_tokenization_spaces=False
)
print(text[0])
<bos><|turn>user Give me a concise overview of these audio files.journal1:<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|>journal2:<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|>journal3:<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|>journal4:<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|>journal5:<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|><turn|> <|turn>model Here is a concise overview of the audio files: **Journal 1:** The speaker felt refreshed, enjoyed a morning ride, a cup of coffee, and was generally happy. **Journal 2:** The speaker spent the afternoon at the park, which was a perfect day for a walk, and enjoyed watching the cherry blossoms. **Journal 3:** The speaker finished the day with a good book, feeling grateful for simple moments and ready for more. **Journal 4:** The speaker returned from work, admiring the sunset, and enjoyed a clear view from the train. **Journal 5:** The speaker had a great lunch with an old friend, enjoyed catching up, and felt happy about the day.<turn|>
Otomatik konuşma çevirisi
Gemma 4 E2B ve E4B, çok dilli konuşma çevirisi görevleri için eğitilmiştir. Bu sayede, seslendirilmiş içeriği doğrudan başka bir dile çevirebilirsiniz. Aşağıdaki kod örneklerinde, Hugging Face Transformers'ı kullanarak modelden seslendirilmiş içeriği metne çevirmesini isteme yöntemi gösterilmektedir:
messages = [
{
"role": "user",
"content": [
{"type": "text", "text": "Transcribe the following speech segment in English, then translate it into Korean. When formatting the answer, first output the transcription in English, then one newline, then output the string 'Korean: ', then the translation in Korean."},
{"type": "audio", "audio": "https://ai.google.dev/gemma/docs/audio/roses-are.wav"},
]
}
]
input_ids = processor.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True, return_dict=True,
return_tensors="pt",
)
input_ids = input_ids.to(model.device, dtype=model.dtype)
outputs = model.generate(**input_ids, max_new_tokens=64)
text = processor.batch_decode(
outputs,
skip_special_tokens=False,
clean_up_tokenization_spaces=False
)
print(text[0])
<bos><|turn>user Transcribe the following speech segment in English, then translate it into Korean. When formatting the answer, first output the transcription in English, then one newline, then output the string 'Korean: ', then the translation in Korean.<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|><turn|> <|turn>model Roses are red, violets are blue. Korean: 장미는 빨갛고, 제비꽃은 파랗다.<turn|>
Otomatik Konuşma Çevirisi / Otomatik Konuşma Tanıma
Kendiniz deneyin
pip install ipywebrtcDaire düğmesine basıp konuşmaya başlayın. İşiniz bittiğinde daire düğmesini tekrar tıklayın. Widget, kaydettiği içeriği hemen oynatmaya başlar.
from google.colab import output
output.enable_custom_widget_manager()
from ipywebrtc import AudioRecorder, CameraStream
camera = CameraStream(constraints={'audio': True,'video':False})
recorder = AudioRecorder(stream=camera)
recorder
AudioRecorder(audio=Audio(value=b'', format='webm'), stream=CameraStream(constraints={'audio': True, 'video': …
webm dosyasını PyTorch'un anlayabileceği wav biçimine dönüştürün.
with open('/content/recording.webm', 'wb') as f:
f.write(recorder.audio.value)
!ffmpeg -i /content/recording.webm /content/recording.wav -y
ffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers
built with gcc 11 (Ubuntu 11.2.0-19ubuntu1)
configuration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared
libavutil 56. 70.100 / 56. 70.100
libavcodec 58.134.100 / 58.134.100
libavformat 58. 76.100 / 58. 76.100
libavdevice 58. 13.100 / 58. 13.100
libavfilter 7.110.100 / 7.110.100
libswscale 5. 9.100 / 5. 9.100
libswresample 3. 9.100 / 3. 9.100
libpostproc 55. 9.100 / 55. 9.100
Input #0, matroska,webm, from '/content/recording.webm':
Metadata:
encoder : Chrome
Duration: 00:00:04.02, start: 0.000000, bitrate: 131 kb/s
Stream #0:0(eng): Audio: opus, 48000 Hz, mono, fltp (default)
Stream mapping:
Stream #0:0 -> #0:0 (opus (native) -> pcm_s16le (native))
Press [q] to stop, [?] for help
Output #0, wav, to '/content/recording.wav':
Metadata:
ISFT : Lavf58.76.100
Stream #0:0(eng): Audio: pcm_s16le ([1][0][0][0] / 0x0001), 48000 Hz, mono, s16, 768 kb/s (default)
Metadata:
encoder : Lavc58.134.100 pcm_s16le
size= 383kB time=00:00:04.01 bitrate= 779.7kbits/s speed=60.6x
video:0kB audio:382kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.019914%
ASR
messages = [{
"role": "user",
"content": [
{"type": "text", "text": "Transcribe the following speech segment in its original language. Follow these specific instructions for formatting the answer:\n* Only output the transcription, with no newlines.\n* When transcribing numbers, write the digits, i.e. write 1.7 and not one point seven, and write 3 instead of three."},
{"type": "audio", "audio": "/content/recording.wav"},
]
}]
input_ids = processor.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True, return_dict=True,
return_tensors="pt",
)
input_ids = input_ids.to(model.device, dtype=model.dtype)
outputs = model.generate(**input_ids, max_new_tokens=64)
text = processor.batch_decode(
outputs,
skip_special_tokens=False,
clean_up_tokenization_spaces=False
)
print(text[0])
<bos><|turn>user Transcribe the following speech segment in its original language. Follow these specific instructions for formatting the answer: * Only output the transcription, with no newlines. * When transcribing numbers, write the digits, i.e. write 1.7 and not one point seven, and write 3 instead of three.<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|><turn|> <|turn>model How can I get to the station?<turn|>
AST
messages = [{
"role": "user",
"content": [
{"type": "text", "text": "Transcribe the following speech segment in English, then translate it into Korean. When formatting the answer, first output the transcription in English, then one newline, then output the string 'Korean: ', then the translation in Korean."},
{"type": "audio", "audio": "/content/recording.wav"},
]
}]
input_ids = processor.apply_chat_template(
messages,
add_generation_prompt=True,
tokenize=True, return_dict=True,
return_tensors="pt",
)
input_ids = input_ids.to(model.device, dtype=model.dtype)
outputs = model.generate(**input_ids, max_new_tokens=64)
text = processor.batch_decode(
outputs,
skip_special_tokens=False,
clean_up_tokenization_spaces=False
)
print(text[0])
<bos><|turn>user Transcribe the following speech segment in English, then translate it into Korean. When formatting the answer, first output the transcription in English, then one newline, then output the string 'Korean: ', then the translation in Korean.<|audio><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><|audio|><audio|><turn|> <|turn>model How can I get to the station? Korean: 역에 어떻게 가나요?<turn|>
Özet ve sonraki adımlar
Bu kılavuzda, Gemma 4 modellerini kullanarak sesi nasıl işleyeceğinizi öğrendiniz. Örneklerde, konuşulan dili metne dönüştürmek için Konuşmayı Metne Dönüştürme (ASR) ve seslendirilmiş içeriği doğrudan başka bir dile çevirmek için Otomatik Konuşma Çevirisi (AST) işlemlerinin nasıl yapılacağı gösterildi. Ayrıca, işleme için not defteri ortamında mikrofondan ses yakalamayı da öğrendiniz.
Daha fazla bilgi için aşağıdaki dokümanları inceleyin.